This commit was manufactured by cvs2svn to create tag

'CVSDB_PRODUCTION'.

git-svn-id: http://viewvc.tigris.org/svn/viewvc/tags/CVSDB_PRODUCTION@80 8cb11bc2-c004-0410-86c3-e597b4017df7

INSTALL

@@ -1,8 +1,8 @@
 INSTALLING VIEWCVS
 ------------------
 
-1) To get viewcvs.cgi to work, make sure that you have Python 1.5.2
-   installed and a webserver which is capable to execute cgi-scripts
+1) To get viewcvs.cgi to work, make sure that you have Python 1.5
+   installed and a webserver which is capable of executing cgi-scripts
    (either based on the .cgi extension, or by placing the script
    within a specific directory).
 
@@ -13,21 +13,29 @@ INSTALLING VIEWCVS
    access to the repository (or a copy of it).  Therefore, rsh/ssh or
    pserver access doesn't work yet.
 
-2) Copy viewcvs.cgi to the cgi-script location of your web
-   server. Edit the file for your specific configuration. In
-   particular, examine the following configuration variables:
+2) Copy viewcvs.cgi to the cgi-script location of your web server.
+
+   If Python is not located in /usr/local/bin, then you'll need to
+   edit the first line of viewcvs.cgi.
+
+3) Copy viewcvs.conf.dist to the same directory and RENAME it to
+   viewcvs.conf
+
+4) Edit viewcvs.conf for your specific configuration. In particular,
+   examine the following configuration options:
 
       cvs_roots
       default_root
       rcs_path
       mime_types_file
 
-   If Python is not located in /usr/local/bin, then you'll need to
-   edit the first line of the file.
+   There are some other options that are usually nice to change. See
+   viewcvs.conf for more information.
 
-   ViewCVS has not been tested on the Win32 platform.
+5) That's it. Try it out.
 
-3) That's it. Try it out.
+   Warning: ViewCVS has not been tested on web servers operating on the
+            Win32 platform.
 
 
 
@@ -62,3 +70,19 @@ If you've trouble to make viewcvs.cgi work:
    or 'httpd' ..
 
  o does viewcvs find your RCS utililties? (edit rcs_path)
+
+=== If something else happens or you can't get it to work:
+
+ o check the ViewCVS home page:
+
+     http://www.lyra.org/greg/python/viewcvs/
+
+ o review the ViewCVS mailing list archive to see if somebody else had
+   the same problem, and it was solved:
+
+     http://mailman.lyra.org/pipermail/viewcvs/
+
+ o send mail to the ViewCVS mailing list: viewcvs@lyra.org
+
+   NOTE: make sure you provide an accurate description of the problem
+         and any relevant tracebacks or error logs.

TODO

@@ -0,0 +1,42 @@
+TODO ITEMS
+----------
+*) add Tamminen Eero's comments on how to make Linux directly execute
+   the Python script. From email on Feb 19.
+   [ add other examples, such as my /bin/sh hack or the teeny CGI stub 
+     importing the bulk hack ]
+
+*) insert rcs_path into PATH before calling "rcsdiff". rcsdiff might
+   use "co" and needs to find it on the path.
+
+*) show the "locked" flag (attach it to the LogEntry objects).
+   Idea from Russell Gordon <russell@hoopscotch.dhs.org>
+
+*) committing with a specific revision number:
+   http://mailman.lyra.org/pipermail/viewcvs/2000q1/000008.html
+
+*) add an "allowed" modules. process the forbidden modules first. any
+   match will throw it out immediately. if an allowed is present, then
+   disallow any module unless it is present in the allowed list.
+
+*) provide a virtual host capability. consider multiple hosts which
+   map a particular Location to the same directory (i.e. the same
+   ViewCVS script and config file). provide for a way to have global
+   options plus vhost-specific options.
+
+*) add capability similar to cvs2cl.pl:
+     http://mailman.lyra.org/pipermail/viewcvs/2000q2/000050.html
+   suggestion from Chris Meyer <cmeyer@gatan.com>.
+
+
+KNOWN BUGS
+----------
+*) from Harri Pasanen, Feb 7: when hideattic is set, files added in a
+   branch are not visible.
+
+*) from Dieter Deyke, Jan 12: if the CVS revisions differ by just a
+   keyword, then the diff output chokes.
+
+*) no scroll bar in Netscape browser when you click "as text" on an
+   HTML document.
+
+*) time.timezone seems to not be available on some 1.5.2 installs

cgi/granny.cgi

@@ -0,0 +1,529 @@
+#!/usr/bin/python
+# -*- Mode: python -*-
+
+"""
+Granny.py - display CVS annotations in HTML
+with lines colored by code age in days.
+
+Original Perl version by J. Gabriel Foster (gabe@sgrail.com)
+   Posted to info-cvs on 02/27/1997
+   You can still get the original shell archive here:
+     http://www.geocrawler.com/archives/3/382/1997/2/0/2103824/
+
+Perl modifications for NT by Marc Paquette (marcpa@cam.org)
+
+Python port and CGI modifications by Brian Lenihan (brianl@real.com)
+
+ From the original granny.pl README:
+
+--
+What is Granny?  Why do I care?
+
+   Granny is a tool for viewing cvs annotation information graphically.  Using
+   Netscape, granny indicates the age of lines by color.  Red lines are new,
+   blue lines are old.  This information can be very useful in determining
+   what lines are 'hot'.  New lines are more likely to contain bugs, and this
+   is an easy way to visualize that information.
+
+     Requirements:
+         Netscape (version 2.0 or better)
+         Perl5
+         CVS 1.9 (1.8 should work, but I have not tried it.)
+
+     Installation:
+         Put granny somewhere in your path.  You may need to edit the
+         first line to point to your perl5 binary and libraries.
+
+     What to do:
+         Run granny just like you would 'cvs annotate' for a single file.
+             granny thefile.C
+
+         To find out who is to blame for that new 'feature'.
+             granny -U thefile.C
+
+         For all your options:
+             granny -h
+
+   Questions, Comments, Assertions?
+     send e-mail to the author: Gabe Foster (gabe@sgrail.com)
+
+   Notes:
+   I'm not the first person to try this sort of display, I just read about it
+   in a magazine somewhere and decided that cvs had all the information
+   I needed.  To whomever first had this idea, it's a great one.
+
+   Granny is free, please use it as you see fit.  I give no warranties.
+   As a courtesy, I ask that you tell me about any modifications you have made,
+   and also ask that you acknowledge my work if you use Granny in your own
+   software.
+--
+
+
+Granny.py:
+
+granny.py [-h][-d days][-i input][-o output][-DUV] file
+
+
+-h:      Get this help display.
+-i:      Specify the input file. (Use - for stdin.)
+-o:      Specify the output file. (Use - for stdout.)
+-d:      Specify the day range for the coloring.\n
+-r:      Specify the cvs revision of the file.
+-D:      Display the date the line was last edited.
+-U       Display the user that last edited the line.
+-V:      Display the version the line was last edited.
+
+By default, granny.py executes cvs annotate on a FILE and
+runs netscape to display the graphic.
+
+It is assumed that cvs and Netscape (for command line version) are
+in your path.
+
+If granny.py is placed in the cgi-bin directory of your Web
+server, it will act as a CGI script. The working directory
+defaults to /usr/tmp, but it can be overridden in the class
+constructor:
+
+     A = CGIAnnotate(tempdir='/tmp')
+
+Required fields:
+
+root        The full path to the cvs root directory.
+Name        The module/filename of the annotated file.
+
+Optional fields:
+
+rev         The cvs revision number to use. (default HEAD).
+
+Set the following fields to display extra info:
+
+showUser    Display the user that last edited the line.
+showVersion Display version that the line was last edited in.
+showDate    Display the date the line was last edited.
+
+http://yourserver.yourdomain.com/cgi-bin/granny.py?root=/cvsroot&Name=module/file
+
+
+TODO:
+
+Add support for determining the MIME type of files and/or a binary check.
+   - easily done by parsing Apache (mime.conf) or Roxen (extensions) MIME 
+files.
+Consider adding buttons to HTML for optional display fields.
+Add support for launching other browsers.
+
+"""
+
+import os
+import sys
+import string
+import re
+import time
+import getopt
+import cStringIO
+import tempfile
+import traceback
+
+
+month_num = {
+     'Jan' : 1, 'Feb' : 2, 'Mar' : 3, 'Apr' : 4, 'May' : 5, 'Jun' : 6,
+      'Jul' : 7, 'Aug' : 8, 'Sep' : 9, 'Oct' : 10, 'Nov' : 11, 'Dec' : 12
+}
+
+class Annotate:
+     def __init__(self):
+         self.day_range = 365
+         self.counter = 0
+         self.color_table = {}
+         self.user = {}
+         self.version = {}
+         self.rtime = {}
+         self.source = {}
+         self.tmp = None
+         self.tmpfile = None
+         self.revision = ''
+         self.showUser = 0
+         self.showDate = 0
+         self.showVersion = 0
+         self.set_today()
+
+
+     def run(self):
+         try:
+             self.process_args()
+             self.parse_raw_annotated_file()
+             self.write_annotated_html_file()
+             if self.tmp:
+                 self.display_annotated_html_file()
+         finally:
+             if sys.exc_info()[0] is not None:
+                 traceback.print_exc()
+             self.cleanup()
+
+
+     def cleanup(self):
+         if self.tmp:
+             self.tmp.close()
+             os.unlink(self.tmpfile)
+         sys.exit(0)
+
+
+     def getoutput(self, cmd):
+         """
+         Get stdin and stderr from cmd and
+         return exit status and captured output
+         """
+
+         if os.name == 'nt':
+             # os.popen is broken on win32, but seems to work so far...
+             pipe = os.popen('%s 2>&1' % cmd, 'r')
+         else:
+             pipe = os.popen('{ %s ; } 2>&1' % cmd, 'r')
+         text = pipe.read()
+         sts = pipe.close()
+         if sts == None:
+             sts = 0
+         if text[:-1] == '\n':
+             text = text[-1:]
+         return sts, text
+
+
+     def set_today(self):
+         """
+         compute the start of this day
+         """
+         (year,mon,day,hour,min,sec,dow,doy,dst) = time.gmtime(time.time())
+         self.today = time.mktime((year,mon,day,0,0,0,0,0,0))
+
+
+     def get_today(self):
+         return self.today
+
+
+     # entify stuff which breaks HTML display
+     # this was lifted from some Zope Code in
+     # StructuredText.py
+     #
+     # XXX try it with string.replace and run it in the profiler
+
+     def html_quote(self,v,
+          character_entities=((re.compile('&'), '&'),
+                              (re.compile("<"), '&lt;' ),
+                              (re.compile(">"), '&gt;' ),
+                              (re.compile('"'), '&quot;'))):
+         gsub = re.sub
+
+         text=str(v)
+         for regexp,name in character_entities:
+             text=gsub(regexp,name,text)
+         return text
+
+
+     def display_annotated_html_file(self):
+         if os.name == 'nt':
+             path = '"C:\\Program Files\\Netscape\\Communicator'\
+                    '\\Program\\Netscape"'
+
+             if os.system('%s %s' % (path, self.tmpfile)) != 0:
+                 sys.stderr.write('%s: Unable to start Netscape' % sys.argv[0])
+                 sys.exit(1)
+         else:
+             if os.system('netscape -remote openFile\(%s\)' %
+                                                          self.tmpfile) != 0:
+                 sys.stderr.write('%s: Trying to run netscape, please wait\n' %
+                                                          sys.argv[0])
+                 if os.system('netscape &') == 0:
+                     for i in range(10):
+                         time.sleep(1)
+                         if os.system('netscape -remote openFile\(%s\)' %
+                                                          self.tmpfile) == 0:
+                             break
+                     if i == 10:
+                         sys.stderr.write('%s:Unable to start netscape\n' %
+                                                          sys.argv[0])
+                 else:
+                     sys.stderr.write('%s:Unable to start netscape\n' %
+                                                          sys.argv[0])
+
+         # give Netscape time to read the file
+         # XXX big files may raise an OSError exception on NT
+         # if the sleep is too short.
+         time.sleep(5)
+
+
+     def get_opts(self):
+         opt_dict = {}
+         if not len(sys.argv[1:]) > 0:
+             self.usage()
+
+         opts, args = getopt.getopt(sys.argv[1:], 'DUVhi:o:d:r:')
+         for k,v in opts:
+             opt_dict[k] = v
+         return opt_dict
+
+
+     def process_args(self):
+         opts = self.get_opts()
+
+         if opts.has_key('-r'):
+             self.revision = '-r%s' % opts['-r']
+
+         if opts.has_key('-h'):
+             self.usage(help=1)
+
+         if opts.has_key('-i'):
+             if opts['-i'] != '-':
+                 self.filename = v
+                 infile = open(filename, 'r')
+                 sys.stdin = infile
+             else:
+                 self.file = sys.stdin
+         else:
+             self.filename = sys.argv[len(sys.argv) - 1]
+
+             cmd = 'cvs annotate %s %s' % (self.revision, self.filename)
+
+             status, text = self.getoutput(cmd)
+
+             if status != 0 or text == '':
+                 sys.stderr.write("Can't run cvs annotate on %s\n" %
+                                                                 self.filename)
+                 sys.stderr.write('%s\n' % text)
+                 sys.exit(1)
+             self.file = cStringIO.StringIO(text)
+
+
+         if opts.has_key('-o'):
+             if opts['-o'] != '-':
+                 outfile = open(v, 'w')
+                 sys.stdout = outfile
+         else:
+             # this could be done without a temp file
+             target = sys.argv[len(sys.argv) -1]
+             self.tmpfile = tempfile.mktemp()
+             self.tmp = open(self.tmpfile, 'w')
+             sys.stdout = self.tmp
+
+
+         if opts.has_key('-d'):
+             if opts['-d'] > 0:
+                 self.day_range = opts['-d']
+
+         if opts.has_key('-D'):
+             self.showDate = 1
+
+         if opts.has_key('-U'):
+             self.showUser = 1
+
+         if opts.has_key('-V'):
+             self.showVersion = 1
+
+
+     def parse_raw_annotated_file(self):
+         ann = re.compile('((\d+\.?)+)\s+\((\w+)\s+(\d\d)-'\
+                          '(\w{3})-(\d\d)\): (.*)')
+
+         text = self.file.read()
+         lines = string.split(text, '\n')
+         for line in lines:
+             # Parse an annotate string
+             m = ann.search(line)
+             if m:
+                 self.version[self.counter] = m.group(1)
+                 self.user[self.counter] = m.group(3)
+                 oldtime = self.today - time.mktime((
+                                                 int(m.group(6)),
+                                                 int(month_num[m.group(5)]),
+                                                 int(m.group(4)),0,0,0,0,0,0))
+
+                 self.rtime[self.counter] = oldtime / 86400
+                 self.source[self.counter] = self.html_quote(m.group(7))
+             else:
+                 self.source[self.counter] = self.html_quote(line)
+                 pass
+             self.counter = self.counter + 1
+
+
+     def write_annotated_html_file(self):
+         if os.environ.has_key('SCRIPT_NAME'):
+             print 'Status: 200 OK\r\n'
+             print 'Content-type: text/html\r\n\r\n'
+
+         print ('<html><head><title>%s</title></head>\n' \
+                '<body bgcolor="#000000">\n' \
+                '<font color="#FFFFFF"><H1>File %s</H1>\n' \
+                '<H3>Code age in days</H2>' % (self.filename, self.filename))
+
+         for i in range(self.day_range + 1):
+             self.color_table[i] = \
+                 self.hsvtorgb(240.0 * i / self.day_range, 1.0, 1.0)
+
+         step = self.day_range / 40
+         if step < 5:
+             step = 1
+             while self.day_range/step > 40:
+                 step = step + 1
+         if step >= 5:
+             if step != 5:
+                 step = step + 5 - (step % 5)
+             while self.day_range / step > 20:
+                 step = step + 5
+
+         for i in range(self.day_range + 1, step):
+             print '<font color=%s>%s ' % (self.color_table[i], i),
+         print '<pre><code>'
+
+         for i in range(self.counter):
+             if self.showUser and self.user.has_key(i):
+                 print '%s%s ' % ('<font color=#FFFFFF>',
+                                  string.ljust(self.user[i],10)),
+
+             if self.showVersion and self.version.has_key(i):
+                 print '%s%s ' % ('<font color=#FFFFFF>',
+                                  string.ljust(self.version[i],6)),
+
+             if self.showDate and self.rtime.has_key(i):
+                 (year,mon,day,hour,min,sec,dow,doy,dst) = time.gmtime(
+                                            self.today - self.rtime[i] * 86400)
+
+                 print '<font color=#FFFFFF>%02d/%02d/%4d ' % (mon, day, year),
+
+
+             if self.rtime.get(i, self.day_range) < self.day_range:
+                 fcolor = self.color_table.get(
+                                         self.rtime[i],
+                                         self.color_table[self.day_range])
+             else:
+                 fcolor = self.color_table[self.day_range]
+
+             print '<font color=%s> %s' % (fcolor, self.source[i])
+
+         print ('</code></pre>\n' \
+                '<font color=#FFFFFF>\n' \
+                '<H5>Granny original Perl version by' \
+                '<I>J. Gabriel Foster</I>\n' \
+                '<ADDRESS><A HREF=\"mailto:gabe@sgrail.com\">'\
+                'gabe@sgrail.com</A></ADDRESS>\n' \
+                'Python version by <I>Brian Lenihan</I>\n' \
+                '<ADDRESS><A HREF=\"mailto:brianl@real.com\">' \
+                'brianl@real.com</A></ADDRESS>\n' \
+                '</body></html>')
+
+         sys.stdout.flush()
+
+
+     def hsvtorgb(self,h,s,v):
+         """
+         a veritable technicolor spew
+         """
+         if s == 0.0:
+             r = v; g = v; b = v
+         else:
+             if h < 0:
+                 h = h + 360.0
+             elif h >= 360.0:
+                 h = h - 360.0
+             h = h / 60.0
+             i = int(h)
+             f = h - i
+
+             if s > 1.0:
+                 s = 1.0
+             p = v * (1.0 - s)
+             q = v * (1.0 - (s * f))
+             t = v * (1.0 - (s * (1.0 - f)))
+
+             if   i == 0: r = v; g = t; b = p
+             elif i == 1: r = q; g = v; b = p
+             elif i == 2: r = p; g = v; b = t
+             elif i == 3: r = p; g = q; b = v
+             elif i == 4: r = t; g = p; b = v
+             elif i == 5: r = v; g = p; b = q
+
+         return '#%02X%02X%02X' % (r * 255 + 0.5, g * 255 + 0.5, b * 255 + 0.5)
+
+
+
+     def usage(self, help=None):
+         sys.stderr.write('\nusage: %s %s\n\n' % (
+                         sys.argv[0],
+                         '[-hDUV][-d days][-i input][-o output][-r rev] FILE')
+         )
+
+         if help is not None:
+             sys.stderr.write(
+                 '-h:      Get this help display.\n' \
+                 '-i:      Specify the input file. (Use - for stdin.)\n' \
+                 '-o:      Specify the output file. (Use - for stdout.)\n' \
+                 '-d:      Specify the day range for the coloring.\n' \
+                 '-r:      Specify the cvs revision of the file.\n' \
+                 '-D:      Display the date the line was last edited.\n' \
+                 '-U       Display the user that last edited the line.\n' \
+                 '-V:      Display the version the line was last edited.\n\n' \
+                 'By default, %s executes a cvs annotate on a FILE and\n' \
+                 'runs netscape to display the graphical ' \
+                 'annotation\n' % sys.argv[0]
+             )
+
+         sys.exit(0)
+
+
+
+class CGIAnnotate(Annotate):
+     def __init__(self,tempdir='/usr/tmp'):
+         Annotate.__init__(self)
+         if os.name == 'nt':
+             self.tempdir = os.environ.get('TEMP') or os.environ.get('TMP')
+         else:
+             # XXX need a sanity check here
+             self.tempdir = tempdir
+         os.chdir(self.tempdir)
+
+     def process_args(self):
+         f = cgi.FieldStorage()
+         cvsroot = f['root'].value
+         if f.has_key('showUser'):
+             self.showUser = 1
+         if f.has_key('showDate'):
+             self.showDate = 1
+         if f.has_key('showVersion'):
+             self.showVersion = 1
+         if f.has_key('rev'):
+             self.revision = '-r%s' % f['rev'].value
+         path = f['Name'].value
+         module = os.path.dirname(path)
+         self.workingdir = 'ann.%s' % os.getpid()
+         self.filename = os.path.basename(path)
+
+         os.mkdir(self.workingdir)
+         os.chdir(os.path.join(self.tempdir, self.workingdir))
+         os.system('cvs -d %s co %s' % (cvsroot, path))
+         os.chdir(module)
+
+         cmd = 'cvs annotate %s %s' % (self.revision, self.filename)
+         status, text = self.getoutput(cmd)
+
+         if status != 0 or text == '':
+             text = "Can't run cvs annotate on %s\n" % path
+         self.file = cStringIO.StringIO(text)
+
+
+     def cleanup(self):
+         os.chdir(self.tempdir)
+         os.system('rm -rf %s' % self.workingdir)
+
+
+     def display_annotated_html_file(self):
+         pass
+
+     def usage(self):
+         pass
+
+if __name__ == '__main__':
+     if os.environ.has_key('SCRIPT_NAME'):
+         import cgi
+         A = CGIAnnotate()
+     else:
+         A = Annotate()
+     A.run()
+

cgi/query.cgi

@@ -0,0 +1,198 @@
+#!/usr/bin/python
+# -*- Mode: python -*-
+#
+# CGI script to process and display queries to CVSdb
+#
+# -----------------------------------------------------------------------
+# Copyright (C) 2000 Jay Painter. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth below:
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
+#
+# -----------------------------------------------------------------------
+#
+# For tracking purposes, this software is identified by:
+#   $Id$
+#
+# -----------------------------------------------------------------------
+
+## BOOTSTRAP
+import sys, os, string
+_viewcvs_root = string.strip(open("/etc/viewcvs/root", "r").read())
+sys.path.append(os.path.join(_viewcvs_root, "lib"))
+##
+
+import cgi, time, cvsdbapi
+
+## tuple of alternating row colors
+Colors = ("#ccccee", "#ffffff")
+
+
+def HTMLHeader():
+    print "Content-type: text/html"
+    print
+    
+
+def FormToCheckinQuery(form):
+    query = cvsdbapi.CreateCheckinQuery()
+
+    if form.has_key("repository"):
+        temp = form["repository"].value
+        query.SetRepository(temp)
+        
+    if form.has_key("branch"):
+        temp = form["branch"].value
+        query.SetBranch(temp)
+        
+    if form.has_key("directory"):
+        temp = form["directory"].value
+        query.SetDirectory(temp)
+
+    if form.has_key("file"):
+        temp = form["file"].value
+        query.SetFile(temp)
+
+    if form.has_key("who"):
+        temp = form["who"].value
+        query.SetAuthor(temp)
+
+    if form.has_key("sortby"):
+        temp = form["sortby"].value
+        if temp == "date":
+            query.SetSortMethod(query.SORT_DATE)
+        elif temp == "author":
+            query.SetSortMethod(query.SORT_AUTHOR)
+        else:
+            query.SetSortMethod(query.SORT_FILE)
+
+    if form.has_key("date"):
+        temp = form["date"].value
+        if temp == "hours":
+            if form.has_key("hours"):
+                hours = string.atoi(form["hours"].value)
+            else:
+                hours = 2
+            query.SetFromDateHoursAgo(hours)
+        elif temp == "day":
+            query.SetFromDateDaysAgo(1)
+        elif temp == "week":
+            query.SetFromDateDaysAgo(7)
+        elif temp == "month":
+            query.SetFromDateDaysAgo(31)
+            
+    return query
+
+
+def PrintCommitRow(commit, color):
+    cTime = commit.GetTime()
+    if not cTime:
+        cTime = "&nbsp";
+    else:
+        cTime = time.strftime("%y/%m/%d %H:%M", time.localtime(cTime))
+    
+    cAuthor = commit.GetAuthor()
+    if not cAuthor:
+        cAuthor = "&nbsp";
+    
+    cFile = os.path.join(commit.GetDirectory(), commit.GetFile())
+    if not cFile:
+        cFile = "&nbsp";
+    
+    cRevision = commit.GetRevision()
+    if not cRevision:
+        cRevision = "&nbsp";
+    
+    cBranch = commit.GetBranch()
+    if not cBranch:
+        cBranch = "&nbsp";
+
+    cPlusMinus = '%d/%d' % (commit.GetPlusCount(), commit.GetMinusCount())
+    
+    cDescription = commit.GetDescription()
+    if not cDescription:
+        cDescription = "&nbsp";
+    else:
+        cDescription = cgi.escape(cDescription)
+        cDescription = string.replace(cDescription, '\n', '<br>')
+    
+    print '<tr bgcolor="%s"><td align=left valign=top>%s</td>\
+           <td align=left valign=top>%s</td>\
+           <td align=left valign=top>%s</td>\
+           <td align=left valign=top>%s</td>\
+           <td align=left valign=top>%s</td>\
+           <td aligh=left valign=top>%s</td>\
+           <td align=left valign=top>%s</td></tr>' % (
+        color, cTime, cAuthor, cFile, cRevision, cBranch,
+        cPlusMinus, cDescription)
+
+
+def PrintCommitRows(commit_list):
+    color_index = 0
+    for commit in commit_list:
+        PrintCommitRow(commit, Colors[color_index])
+        color_index = (color_index + 1) % len(Colors)
+
+
+g_iColorIndex = 0
+def CommitCallback(commit):
+    global g_iColorIndex
+    PrintCommitRow(commit, Colors[g_iColorIndex])
+    g_iColorIndex = (g_iColorIndex + 1) % len(Colors)
+
+
+def RunQuery(query):
+    query.SetCommitCB(CommitCallback)
+    db = cvsdbapi.ConnectDatabaseReadOnly()
+    db.RunQuery(query)
+
+
+class HTMLTemplate:
+    def __init__(self, filename):
+        self.template = open(filename, 'r').read()
+
+    def Print1(self):
+        index = string.find(self.template, '<!-- INSERT QUERY ROWS -->')
+        print self.template[:index]
+
+    def Print2(self):
+        index = string.find(self.template, '<!-- INSERT QUERY ROWS -->')
+        print self.template[index:]
+
+
+def Main():
+    HTMLHeader()
+
+    template_path = os.path.join(
+        _viewcvs_root, "html-templates", "querytemplate.html")
+    template = HTMLTemplate(template_path)
+    template.Print1()
+    
+    form = cgi.FieldStorage()
+    query = FormToCheckinQuery(form)
+    RunQuery(query)
+    
+    template.Print2()
+
+
+if __name__ == '__main__':
+    Main()

cgi/queryform.cgi

@@ -0,0 +1,59 @@
+#!/usr/bin/python
+# -*- Mode: python -*-
+#
+# nothing here yet!
+#
+# -----------------------------------------------------------------------
+# Copyright (C) 2000 Jay Painter. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth below:
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
+#
+# -----------------------------------------------------------------------
+#
+# For tracking purposes, this software is identified by:
+#   $Id$
+#
+# -----------------------------------------------------------------------
+
+## BOOTSTRAP
+import sys, os, string
+_viewcvs_root = string.strip(open("/etc/viewcvs/root", "r").read())
+sys.path.append(os.path.join(_viewcvs_root, "lib"))
+##
+
+
+def HTMLHeader():
+    print "Content-type: text/html"
+    print
+    
+
+def Main():
+    HTMLHeader()
+    template_path = os.path.join(
+        _viewcvs_root, "html-templates", "queryformtemplate.html")
+    print open(template_path, "r").read()
+
+
+if __name__ == '__main__':
+    Main()

cgi/viewcvs.conf.dist

@@ -0,0 +1,381 @@
+#---------------------------------------------------------------------------
+#
+# Configuration file for ViewCVS
+#
+# Information on ViewCVS is located at the following web site:
+#     http://www.lyra.org/viewcvs/
+#
+#---------------------------------------------------------------------------
+
+#
+# BASIC CONFIGURATION
+#
+# For correct operation, you will probably need to change the following
+# configuration variables:
+#
+#    cvs_roots
+#    default_root
+#    rcs_path
+#    mime_types_file
+#
+# It is usually desirable to change the following variables:
+#
+#    address
+#    main_title
+#    logo
+#    forbidden
+#
+#    long_intro
+#    repository_info
+#
+# For Python source colorization:
+#
+#    py2html_path
+#
+# If your icons are in a special location:
+#
+#    icons
+#
+
+#
+# FORMAT INFORMATION
+#
+# This file is delineated by sections, specified in [brackets]. Within each
+# section, are a number of configuration settings. These settings take the
+# form of: name = value. Values may be continued on the following line by
+# indenting the continued line.
+#
+# WARNING: indentation *always* means continuation. name=value lines should
+#          always start in column zero.
+#
+# Comments should always start in column zero, and are identified with "#".
+#
+# Certain configuration settings may have multiple values. These should be
+# separated by a comma. The settings where this is allowed are noted below.
+#
+# Any other setting that requires special syntax is noted at that setting.
+# 
+
+#---------------------------------------------------------------------------
+[general]
+
+#
+# This setting specifies each of the CVS roots on your system and assigns
+# names to them. Each root should be given by a "name: path" value. Multiple
+# roots should be separated by commas.
+#
+cvs_roots =
+	Development : /home/cvsroot
+
+# this is the name of the default CVS root.
+default_root = Development
+
+# uncomment if the RCS binaries are not on the standard path
+# NOTE: the trailing slash is required!
+#rcs_path = /usr/bin/
+
+#
+# This is a pathname to a MIME types file to help viewcvs to guess the
+# correct MIME type on checkout.
+#
+# If you are having problems with the default guess on the MIME type, then
+# uncomment this option and point it at a MIME type file.
+#
+# For example, you can use the mime.types from apache here:
+#mime_types_file = /usr/local/apache/conf/mime.types
+
+# This address is shown in the footer. It should contain the CVS maintainer.
+address = <a href="mailto:gstein@lyra.org">gstein@lyra.org</a>
+
+# this title is used on the main entry page
+main_title = CVS Repository
+
+#
+# This should contain a list of modules in the repository that should not be
+# displayed (by default or by explicit path specification).
+#
+forbidden =
+# forbidden = example
+# forbidden = example1, example2
+
+#---------------------------------------------------------------------------
+[cvsdb]
+
+host = master
+database_name = bonsai
+user = root
+passwd = ogieta50
+readonly_user = root
+readonly_passwd = ogieta50
+
+#---------------------------------------------------------------------------
+[images]
+#
+# All images are defined with three values: URL, WIDTH, HEIGHT
+#
+
+# this logo will appear on the page
+logo = /icons/apache_pb.gif, 259, 32
+
+#
+# these icons represent a back-pointer, a directory (folder), and a file.
+# they are normally available in a standard Apache distribution, along
+# with larger versions if these are too small for you.
+#
+back_icon = /icons/small/back.gif, 16, 16
+dir_icon  = /icons/small/dir.gif, 16, 16
+file_icon = /icons/small/text.gif, 16, 16
+
+#---------------------------------------------------------------------------
+[colors]
+
+# background color of log entry in markup
+markup_log = #ffffff
+
+# color of change-section headings in a diff
+diff_heading = #99cccc
+
+# color of "empty" lines
+diff_empty = #cccccc
+
+# removed lines
+diff_remove = #ff9999
+
+# changed lines
+diff_change = #99ff99
+
+# added lines
+diff_add = #ccccff
+
+# empty lines in a change block (one part smaller than the other)
+diff_dark_change = #99cc99
+
+# even/odd row colors
+even_odd = #ccccee, #ffffff
+
+# navigation header (in diff screen, file view, annotation, etc)
+nav_header = #9999ee
+
+# color of text on most pages
+text = #000000
+
+# color of standard background
+background = #ffffff
+
+# color of alternate background (diffs, file view, annotations, etc)
+alt_background = #eeeeee
+
+# table header colors (normal and the sorted-by column)
+column_header_normal = #cccccc
+column_header_sorted = #88ff88
+
+# Uncomment the following line for colored borders in tables
+#table_border = #999999
+
+#---------------------------------------------------------------------------
+[text]
+
+#
+# WARNING: if you continue the text onto multiple lines, then make SURE that
+#          you indent the continuations.
+#
+
+short_intro =
+    <p>
+    Click on a directory to enter that directory. Click on a file to display
+    its revision history and to get a chance to display diffs between
+    revisions. 
+    </p>
+
+long_intro =
+    <p>
+    This is a WWW interface for CVS Repositories.
+    You can browse the file hierarchy by picking directories
+    (which have slashes after them, <i>e.g.</i>, <b>src/</b>).
+    If you pick a file, you will see the revision history
+    for that file.
+    Selecting a revision number will download that revision of
+    the file.  There is a link at each revision to display
+    diffs between that revision and the previous one, and
+    a form at the bottom of the page that allows you to
+    display diffs between arbitrary revisions.
+    </p>
+    <p>
+    This script
+    (<a href="http://www.lyra.org/viewcvs/">ViewCVS</a>)
+    has been written by Greg Stein
+    &lt;<a href="mailto:gstein@lyra.org">gstein@lyra.org</a>&gt;
+    based on the
+    <a href="http://linux.fh-heilbronn.de/~zeller/cgi/cvsweb.cgi">cvsweb</a>
+    script by Henner Zeller
+    &lt;<a href="mailto:zeller@think.de">zeller@think.de</a>&gt;;
+    it is covered by the
+    <a href="http://www.opensource.org/licenses/bsd-license.html">BSD
+    Licence</a>.
+    If you would like to use this CGI script on your own web server and
+    CVS tree, see Greg's
+    <a href="http://www.lyra.org/viewcvs/">ViewCVS distribution
+    site</a>.
+    Please send any suggestions, comments, etc. to
+    <a href="mailto:gstein@lyra.org">Greg Stein</a>.
+    </p>
+
+doc_info =
+    <h3>CVS Documentation</h3>
+    <blockquote>
+    <p>
+    <a href="http://www.loria.fr/~molli/cvs/doc/cvs_toc.html">CVS
+      User's Guide</a><br>
+    <a href="http://www.arc.unm.edu/~rsahu/cvs.html">CVS Tutorial</a><br>
+    <a href="http://cellworks.washington.edu/pub/docs/cvs/tutorial/cvs_tutorial_1.html">Another CVS tutorial</a><br>
+    <a href="http://www.csc.calpoly.edu/~dbutler/tutorials/winter96/cvs/">Yet
+      another CVS tutorial (a little old, but nice)</a><br>
+    <a href="http://www.cs.utah.edu/dept/old/texinfo/cvs/FAQ.txt">An old but
+      very useful FAQ about CVS</a>
+    </p>
+    </blockquote>
+
+repository_info =
+    <!-- insert repository access instructions here -->
+
+#---------------------------------------------------------------------------
+[options]
+### DOC
+
+# sort_by: File sort order
+#   file   Sort by filename
+#   rev    Sort by revision number
+#   date   Sort by commit date
+#   author Sort by author
+#   log    Sort by log message
+sort_by = file
+
+# hide_attic: Hide or show files in Attic
+#   1      Hide files in Attic
+#   0      Show files in Attic
+hide_attic = 1
+
+# log_sort: Sort order for CVS logs
+#   date   Sort revisions by date
+#   rev    Sort revision by revision number
+#   cvs    Don't sort them. Same order as CVS/RCS shows them.
+log_sort = date
+
+# diff_format: Default diff format
+#   h      Human readable
+#   u      Unified diff
+#   c      Context diff
+#   s      Side by side
+#   H      Long human readable
+diff_format = h
+
+# hide_cvsroot: Don't show the CVSROOT directory
+#   1      Hide CVSROOT directory
+#   0      Show CVSROOT directory
+hide_cvsroot = 1
+
+# hide_non_readable: Don't show entries which cannot be read
+#   1      Hide non-readable entries
+#   0      Show non-readble entries
+hide_non_readable = 1
+
+# Show author of last change
+show_author = 1
+
+# set to 1 to make lines break at spaces,
+# set to 0 to make no-break lines,
+# set to a positive integer to make the lines cut at that length
+hr_breakable = 1
+
+# give out function names in human readable diffs
+# this just makes sense if we have C-files, otherwise
+# diff's heuristic doesn't work well ..
+# ( '-p' option to diff)
+hr_funout = 0
+
+# ignore whitespaces for human readable diffs
+# (indendation and stuff ..)
+# ( '-w' option to diff)
+hr_ignore_white = 1
+
+# ignore diffs which are caused by
+# keyword-substitution like $Id - Stuff
+# ( '-kk' option to rcsdiff)
+hr_ignore_keyword_subst = 1
+
+# allow annotation of files.
+# NOTE: this requires rw-access to the CVSROOT/history file, and rw-access to
+# the subdirectory to place the lock... so you maybe don't want it
+# WARNING: this is not yet implemented!!
+allow_annotate = 0
+
+# allow pretty-printed version of files
+allow_markup = 1
+
+# allow compression with gzip of output if the Browser accepts it
+# (HTTP_ACCEPT_ENCODING=gzip)
+# [make sure to have gzip in the path]
+allow_compress = 1
+
+# Make use of javascript functions to skip the need for submitting a form.
+# For example, this way you can select one of your CVS roots without
+# pressing 'Go' (... if you have more than one CVSROOT defined)
+use_java_script = 1
+
+# open Download-Links in another window
+open_extern_window = 1
+
+# The size of this extern window; this size option needs use_java_script
+# to be defined
+extern_window_width = 600
+extern_window_height = 440
+
+# If you have files which automatically refers to other files
+# (such as HTML) then this allows you to browse the checked
+# out files as if outside CVS.
+checkout_magic = 1
+
+# Show last changelog message for sub directories
+# The current implementation makes many assumptions and may show the
+# incorrect file at some times. The main assumption is that the last
+# modified file has the newest filedate. But some CVS operations
+# touches the file without even when a new version is't checked in,
+# and TAG based browsing essientially puts this out of order, unless
+# the last checkin was on the same tag as you are viewing.
+# Enable this if you like the feature, but don't rely on correct results.
+show_subdir_lastmod = 0
+
+# show a portion of the most recent log entry in directory listings
+show_logs = 1
+
+# Show CVS log when viewing file contents
+show_log_in_markup = 1
+
+# == Configuration defaults ==
+# Defaults for configuration variables that shouldn't need
+# to be configured..
+allow_version_select = 1
+
+#
+# If you want to use Marc-Andrew Lemburg's py2html (and Just van Rossum's
+# PyFontify) to colorize Python files, then you may need to change this
+# variable to point to their directory location.
+#
+# This directory AND the standard Python path will be searched.
+#
+py2html_path = .
+#py2html_path = /usr/local/lib/python1.5/site-python
+
+# the length to which the most recent log entry should be truncated when
+# shown in the directory view
+short_log_len = 80
+
+table_padding = 2
+
+diff_font_face = Helvetica,Arial
+diff_font_size = -1
+
+# the width of the textinput in the request-diff-form
+input_text_size = 12
+
+#---------------------------------------------------------------------------

html-templates/queryformtemplate.html

@@ -0,0 +1,81 @@
+<html>
+<head><title>CVSdb Query Form</title></head>
+<body bgcolor="#ffffff">
+
+<h1>CVSdb Query Form for GNOME CVS Repository</h1>
+
+<form method=get action='query.cgi'>
+<table border cellpading=8 cellspacing=0>
+
+  <tr>
+    <td align=right>Repository:</td>
+    <td><input type=text name=repository size=25></td>
+  </tr>
+
+  <tr>
+    <td align=right>Branch:</td>
+    <td><input type=text name=branch size=25></td>
+  </tr>
+
+  <tr>
+    <td align=right>Directory:</td>
+    <td><input type=text name=directory value='' size=45></td>
+  </tr>
+
+  <tr>
+    <td align=right>File:</td>
+    <td><input type=text name=file value='' size=45></td>
+  </tr>
+
+  <tr>
+    <td align=right>Who:</td>
+    <td><input type=text name=who value='' size=45></td>
+  </tr>
+
+  <tr>
+    <td align=right>Sort By:</td>
+    <td>
+      <select name=sortby>
+        <option value="date">Date</option>
+        <option value="author">Author</option>
+        <option value="file">File</option>
+      </select>
+    </td>
+  </tr>
+
+  <tr>
+    <td align=right valign=top><br>Date:</td>
+    <td colspan=2>
+      <table BORDER=0 CELLSPACING=0 CELLPADDING=0>
+        <tr>
+          <td><input type=radio name=date checked value=hours></td>
+          <td>
+            In the last <input type=text name=hours value=2 size=4> hours
+          </td>
+        </tr>
+        <tr>
+          <td><input type=radio name=date value=day></td>
+          <td>In the last day</td>
+        </tr>
+        <tr>
+          <td><input type=radio name=date value=week></td>
+          <td>In the last week</td>
+        </tr>
+        <tr>
+          <td><input type=radio name=date value=month></td>
+          <td>In the last month</td>
+        </tr>
+        <tr>
+          <td><input type=radio name=date value=all></td>
+          <td>Since the beginning of time</td>
+        </tr>
+      </table>
+    </td>
+  </tr>
+  <tr>
+    <td colspan=2><input type=submit value='Run Query'></td>
+  </tr>
+</table>
+</form>
+
+</html>

html-templates/querytemplate.html

@@ -0,0 +1,30 @@
+<html>
+<head><title>CVSdb Query</title></head>
+<body bgcolor="#ffffff">
+
+<h1>CVSdb Query</h1>
+
+<table width="100%" border=0 cellspacing=0 cellpadding=2>
+  <tr bgcolor="#88ff88">
+    <th align=left valign=top>Date</th>
+    <th align=left valign=top>Author</th>
+    <th align=left valign=top>File</th>
+    <th align=left valign=top>Revision</th>
+    <th align=left valign=top>Branch</th>
+    <th align=left valign=top>+/-</th>
+    <th align=left valign=top>Description</th>
+  </tr>
+  <!-- INSERT QUERY ROWS -->
+  <tr bgcolor="#88ff88">
+    <th align=left valign=top>&nbsp</th>
+    <th align=left valign=top>&nbsp</th>
+    <th align=left valign=top>&nbsp</th>
+    <th align=left valign=top>&nbsp</th>
+    <th align=left valign=top>&nbsp</th>
+    <th align=left valign=top>&nbsp</th>
+    <th align=left valign=top>&nbsp</th>
+  </tr>
+</table>
+
+</body>
+</html>

lib/PyFontify.py

@@ -0,0 +1,153 @@
+"""Module to analyze Python source code; for syntax coloring tools.
+
+Interface:
+	tags = fontify(pytext, searchfrom, searchto)
+
+The 'pytext' argument is a string containing Python source code.
+The (optional) arguments 'searchfrom' and 'searchto' may contain a slice in pytext. 
+The returned value is a list of tuples, formatted like this:
+	[('keyword', 0, 6, None), ('keyword', 11, 17, None), ('comment', 23, 53, None), etc. ]
+The tuple contents are always like this:
+	(tag, startindex, endindex, sublist)
+tag is one of 'keyword', 'string', 'comment' or 'identifier'
+sublist is not used, hence always None. 
+"""
+
+# Based on FontText.py by Mitchell S. Chapman,
+# which was modified by Zachary Roadhouse,
+# then un-Tk'd by Just van Rossum.
+# Many thanks for regular expression debugging & authoring are due to:
+#	Tim (the-incredib-ly y'rs) Peters and Cristian Tismer
+# So, who owns the copyright? ;-) How about this:
+# Copyright 1996-1997: 
+#	Mitchell S. Chapman,
+#	Zachary Roadhouse,
+#	Tim Peters,
+#	Just van Rossum
+
+__version__ = "0.3.1"
+
+import string, regex
+
+# First a little helper, since I don't like to repeat things. (Tismer speaking)
+import string
+def replace(where, what, with):
+	return string.join(string.split(where, what), with)
+
+# This list of keywords is taken from ref/node13.html of the
+# Python 1.3 HTML documentation. ("access" is intentionally omitted.)
+keywordsList = [
+	"del", "from", "lambda", "return",
+	"and", "elif", "global", "not", "try",
+	"break", "else", "if", "or", "while",
+	"class", "except", "import", "pass",
+	"continue", "finally", "in", "print",
+	"def", "for", "is", "raise"]
+
+# Build up a regular expression which will match anything
+# interesting, including multi-line triple-quoted strings.
+commentPat = "#.*"
+
+pat = "q[^\q\n]*\(\\\\[\000-\377][^\q\n]*\)*q"
+quotePat = replace(pat, "q", "'") + "\|" + replace(pat, 'q', '"')
+
+# Way to go, Tim!
+pat = """
+	qqq
+	[^\\q]*
+	\(
+		\(	\\\\[\000-\377]
+		\|	q
+			\(	\\\\[\000-\377]
+			\|	[^\\q]
+			\|	q
+				\(	\\\\[\000-\377]
+				\|	[^\\q]
+				\)
+			\)
+		\)
+		[^\\q]*
+	\)*
+	qqq
+"""
+pat = string.join(string.split(pat), '')	# get rid of whitespace
+tripleQuotePat = replace(pat, "q", "'") + "\|" + replace(pat, 'q', '"')
+
+# Build up a regular expression which matches all and only
+# Python keywords. This will let us skip the uninteresting
+# identifier references.
+# nonKeyPat identifies characters which may legally precede
+# a keyword pattern.
+nonKeyPat = "\(^\|[^a-zA-Z0-9_.\"']\)"
+
+keyPat = nonKeyPat + "\("
+for keyword in keywordsList:
+	keyPat = keyPat + keyword + "\|"
+keyPat = keyPat[:-2] + "\)" + nonKeyPat
+
+matchPat = keyPat + "\|" + commentPat + "\|" + tripleQuotePat + "\|" + quotePat
+matchRE = regex.compile(matchPat)
+
+idKeyPat = "[ \t]*[A-Za-z_][A-Za-z_0-9.]*"	# Ident w. leading whitespace.
+idRE = regex.compile(idKeyPat)
+
+
+def fontify(pytext, searchfrom = 0, searchto = None):
+	if searchto is None:
+		searchto = len(pytext)
+	# Cache a few attributes for quicker reference.
+	search = matchRE.search
+	group = matchRE.group
+	idSearch = idRE.search
+	idGroup = idRE.group
+	
+	tags = []
+	tags_append = tags.append
+	commentTag = 'comment'
+	stringTag = 'string'
+	keywordTag = 'keyword'
+	identifierTag = 'identifier'
+	
+	start = 0
+	end = searchfrom
+	while 1:
+		start = search(pytext, end)
+		if start < 0 or start >= searchto:
+			break	# EXIT LOOP
+		match = group(0)
+		end = start + len(match)
+		c = match[0]
+		if c not in "#'\"":
+			# Must have matched a keyword.
+			if start <> searchfrom:
+				# there's still a redundant char before and after it, strip!
+				match = match[1:-1]
+				start = start + 1
+			else:
+				# this is the first keyword in the text.
+				# Only a space at the end.
+				match = match[:-1]
+			end = end - 1
+			tags_append((keywordTag, start, end, None))
+			# If this was a defining keyword, look ahead to the
+			# following identifier.
+			if match in ["def", "class"]:
+				start = idSearch(pytext, end)
+				if start == end:
+					match = idGroup(0)
+					end = start + len(match)
+					tags_append((identifierTag, start, end, None))
+		elif c == "#":
+			tags_append((commentTag, start, end, None))
+		else:
+			tags_append((stringTag, start, end, None))
+	return tags
+
+
+def test(path):
+	f = open(path)
+	text = f.read()
+	f.close()
+	tags = fontify(text)
+	for tag, start, end, sublist in tags:
+		print tag, `text[start:end]`

lib/cfg.py

@@ -0,0 +1,48 @@
+# -*- Mode: python -*-
+# -----------------------------------------------------------------------
+# Copyright (C) 2000 Jay Painter. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth below:
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
+#
+# -----------------------------------------------------------------------
+#
+# For tracking purposes, this software is identified by:
+#   $Id$
+#
+# -----------------------------------------------------------------------
+
+class EmptyNameSpace:
+    "Placehoder empty class for nesting namespaces."
+    pass
+
+
+
+## [cvsdb]
+cvsdb = EmptyNameSpace()
+cvsdb.host = 'master'
+cvsdb.database_name = 'bonsai'
+cvsdb.user = 'root'
+cvsdb.passwd = 'ogieta50'
+cvsdb.readonly_user = 'root'
+cvsdb.readonly_passwd = 'ogieta50' 

lib/commit.py

@@ -0,0 +1,179 @@
+# -*- Mode: python -*-
+# -----------------------------------------------------------------------
+# Copyright (C) 2000 Jay Painter. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth below:
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
+#
+# -----------------------------------------------------------------------
+#
+# For tracking purposes, this software is identified by:
+#   $Id$
+#
+# -----------------------------------------------------------------------
+
+import os
+
+## the Commit class holds data on one commit, the representation is as
+## close as possible to how it should be committed and retrieved to the
+## database engine
+
+class Commit:
+    
+    ## static constants for type of commit
+    CHANGE = 0
+    ADD = 1
+    REMOVE = 2
+    
+    def __init__(self):
+        self.__directory = ''
+        self.__file = ''
+        self.__repository = ''
+        self.__revision = ''
+        self.__author = ''
+        self.__branch = ''
+        self.__pluscount = ''
+        self.__minuscount = ''
+        self.__description = ''
+        self.__gmt_time = 0.0
+        self.__type = Commit.CHANGE
+
+    def SetRepository(self, repository):
+        ## clean up repository path; make sure it doesn't end with a
+        ## path seperator
+        while repository[-1] == os.sep:
+            repository = repository[:-1]
+
+        self.__repository = repository
+
+    def GetRepository(self):
+        return self.__repository
+        
+    def SetDirectory(self, dir):
+        ## clean up directory path; make sure it doesn't begin
+        ## or end with a path seperator
+        while dir[0] == os.sep:
+            dir = dir[1:]
+        while dir[-1] == os.sep:
+            dir = dir[:-1]
+        
+        self.__directory = dir
+
+    def GetDirectory(self):
+        return self.__directory
+
+    def SetFile(self, file):
+        ## clean up filename; make sure it doesn't begin
+        ## or end with a path seperator
+        while file[0] == os.sep:
+            file = file[1:]
+        while file[-1] == os.sep:
+            file = file[:-1]
+        
+        self.__file = file
+
+    def GetFile(self):
+        return self.__file
+        
+    def SetRevision(self, revision):
+        self.__revision = revision
+
+    def GetRevision(self):
+        return self.__revision
+
+    def SetTime(self, gmt_time):
+        self.__gmt_time = float(gmt_time)
+
+    def GetTime(self):
+        return self.__gmt_time
+
+    def SetAuthor(self, author):
+        self.__author = author
+
+    def GetAuthor(self):
+        return self.__author
+
+    def SetBranch(self, branch):
+        if not branch:
+            self.__branch = ''
+        else:
+            self.__branch = branch
+
+    def GetBranch(self):
+        return self.__branch
+
+    def SetPlusCount(self, pluscount):
+        self.__pluscount = pluscount
+
+    def GetPlusCount(self):
+        return self.__pluscount
+
+    def SetMinusCount(self, minuscount):
+        self.__minuscount = minuscount
+
+    def GetMinusCount(self):
+        return self.__minuscount
+
+    def SetDescription(self, description):
+        self.__description = description
+
+    def GetDescription(self):
+        return self.__description
+
+    def SetTypeChange(self):
+        self.__type = Commit.CHANGE
+
+    def SetTypeAdd(self):
+        self.__type = Commit.ADD
+
+    def SetTypeRemove(self):
+        self.__type = Commit.REMOVE
+
+    def GetType(self):
+        return self.__type
+
+    def GetTypeString(self):
+        if self.__type == Commit.CHANGE:
+            return 'Change'
+        elif self.__type == Commit.ADD:
+            return 'Add'
+        elif self.__type == Commit.REMOVE:
+            return 'Remove'
+
+
+## entrypoints
+        
+def CreateCommit():
+    return Commit()
+
+
+def PrintCommit(commit):
+    print os.path.join(commit.GetDirectory(), commit.GetFile()),\
+          commit.GetRevision(),\
+          commit.GetAuthor()
+        
+    if commit.GetBranch():
+        print commit.GetBranch()
+    print commit.GetDescription()
+    print
+

lib/compat.py

@@ -0,0 +1,40 @@
+#
+# ### add license stuff
+#
+# compat.py: compatibility functions for operation across Python 1.5.x
+#
+
+import urllib
+import string
+import time
+import re
+
+#
+# urllib.urlencode() is new to Python 1.5.2
+#
+try:
+  urlencode = urllib.urlencode
+except AttributeError:
+  def urlencode(dict):
+    "Encode a dictionary as application/x-url-form-encoded."
+    if not dict:
+      return ''
+    quote = urllib.quote_plus
+    keyvalue = [ ]
+    for key, value in dict.items():
+      keyvalue.append(quote(key) + '=' + quote(str(value)))
+    return '?' + string.join(keyvalue, '&')
+
+#
+# time.strptime() is new to Python 1.5.2
+#
+if hasattr(time, 'strptime'):
+  def cvs_strptime(timestr):
+    return time.strptime(timestr, '%Y/%m/%d %H:%M:%S')
+else:
+  _re_rev_date = re.compile('([0-9]{4})/([0-9][0-9])/([0-9][0-9]) '
+                            '([0-9][0-9]):([0-9][0-9]):([0-9][0-9])')
+  def cvs_strptime(timestr):
+    matches = _re_rev_date.match(timestr).groups()
+    return tuple(map(int, matches)) + (0, 1, -1)
+cvs_strptime.__doc__ = 'Parse a CVS-style date/time value.'

lib/config.py

@@ -0,0 +1,214 @@
+#
+# ### add license stuff
+#
+# config.py: configuration utilities
+#
+
+import sys
+import os
+import string
+import ConfigParser
+
+
+#########################################################################
+#
+# CONFIGURATION
+#
+# There are three forms of configuration:
+#
+#       1) copy viewcvs.conf.dist to viewcvs.conf and edit
+#       2) as (1), but delete all unchanged entries from viewcvs.conf
+#       3) do not use viewcvs.conf and just edit the defaults in this file
+#
+# Most users will want to use (1), but there are slight speed advantages
+# to the other two options. Note that viewcvs.conf values are a bit easier
+# to work with since it is raw text, rather than python literal values.
+#
+#########################################################################
+
+class Config:
+  _sections = ('general', 'images', 'options', 'colors', 'text', 'cvsdb')
+  _force_multi_value = ('cvs_roots', 'forbidden', 'even_odd')
+
+  def __init__(self):
+    for section in self._sections:
+      setattr(self, section, _sub_config())
+
+  def load_config(self, fname):
+    this_dir = os.path.dirname(sys.argv[0])
+    pathname = os.path.join(this_dir, fname)
+    parser = ConfigParser.ConfigParser()
+    parser.read(pathname)
+
+    for section in self._sections:
+      if not parser.has_section(section):
+        continue
+
+      sc = getattr(self, section)
+
+      for opt in parser.options(section):
+        value = parser.get(section, opt)
+        if opt in self._force_multi_value or section == 'images':
+          value = map(string.strip, string.split(value, ','))
+        else:
+          try:
+            value = int(value)
+          except ValueError:
+            pass
+
+        if opt == 'cvs_roots':
+          roots = { }
+          for root in value:
+            name, path = map(string.strip, string.split(root, ':'))
+            roots[name] = path
+          value = roots
+        setattr(sc, opt, value)
+
+  def set_defaults(self):
+    "Set some default values in the configuration."
+
+    self.general.cvs_roots = {
+      # user-visible-name : path
+      "Development" : "/home/cvsroot",
+      }
+    self.general.default_root = "Development"
+    self.general.rcs_path = ''
+    self.general.mime_types_file = ''
+    self.general.address = '<a href="mailto:gstein@lyra.org">gstein@lyra.org</a>'
+    self.general.main_title = 'CVS Repository'
+    self.general.forbidden = ()
+
+    self.cvsdb.enabled = 0
+    self.cvsdb.host = ''
+    self.cvsdb.database_name = ''
+    self.cvsdb.user = ''
+    self.cvsdb.passwd = ''
+    self.cvsdb.readonly_user = ''
+    self.cvsdb.readonly_passwd = '' 
+
+    self.images.logo = "/icons/apache_pb.gif", 259, 32
+    self.images.back_icon = "/icons/small/back.gif", 16, 16
+    self.images.dir_icon = "/icons/small/dir.gif",  16, 16
+    self.images.file_icon = "/icons/small/text.gif", 16, 16
+
+    self.colors.markup_log = "#ffffff"
+
+    self.colors.diff_heading = "#99cccc"
+    self.colors.diff_empty = "#cccccc"
+    self.colors.diff_remove = "#ff9999"
+    self.colors.diff_change = "#99ff99"
+    self.colors.diff_add = "#ccccff"
+    self.colors.diff_dark_change = "#99cc99"
+
+    self.colors.even_odd = ("#ccccee", "#ffffff")
+
+    self.colors.nav_header = "#9999ee"
+
+    self.colors.text = "#000000"
+    self.colors.background = "#ffffff"
+    self.colors.alt_background = "#eeeeee"
+
+    self.colors.column_header_normal = "#cccccc"
+    self.colors.column_header_sorted = "#88ff88"
+
+    self.colors.table_border = None	# no border
+
+    self.options.sort_by = 'file'
+    self.options.hide_attic = 1
+    self.options.log_sort = 'date'
+    self.options.diff_format = 'h'
+    self.options.hide_cvsroot = 1
+    self.options.hide_non_readable = 1
+    self.options.show_author = 1
+    self.options.hr_breakable = 1
+    self.options.hr_funout = 1
+    self.options.hr_ignore_white = 1
+    self.options.hr_ignore_keyword_subst = 1
+    self.options.allow_annotate = 0	### doesn't work yet!
+    self.options.allow_markup = 1
+    self.options.allow_compress = 1
+    self.options.use_java_script = 1
+    self.options.open_extern_window = 1
+    self.options.extern_window_width = 600
+    self.options.extern_window_height = 440
+    self.options.checkout_magic = 1
+    self.options.show_subdir_lastmod = 0
+    self.options.show_logs = 1
+    self.options.show_log_in_markup = 1
+    self.options.allow_version_select = 1
+    self.options.py2html_path = '.'
+    self.options.short_log_len = 80
+    self.options.table_padding = 2
+    self.options.diff_font_face = 'Helvetica,Arial'
+    self.options.diff_font_size = -1
+    self.options.input_text_size = 12
+
+    self.text.long_intro = """\
+    <p>
+    This is a WWW interface for CVS Repositories.
+    You can browse the file hierarchy by picking directories
+    (which have slashes after them, <i>e.g.</i>, <b>src/</b>).
+    If you pick a file, you will see the revision history
+    for that file.
+    Selecting a revision number will download that revision of
+    the file.  There is a link at each revision to display
+    diffs between that revision and the previous one, and
+    a form at the bottom of the page that allows you to
+    display diffs between arbitrary revisions.
+    </p>
+    <p>
+    This script
+    (<a href="http://www.lyra.org/viewcvs/">ViewCVS</a>)
+    has been written by Greg Stein
+    &lt;<a href="mailto:gstein@lyra.org">gstein@lyra.org</a>&gt;
+    based on the
+    <a href="http://linux.fh-heilbronn.de/~zeller/cgi/cvsweb.cgi">cvsweb</a>
+    script by Henner Zeller
+    &lt;<a href="mailto:zeller@think.de">zeller@think.de</a>&gt;;
+    it is covered by the
+    <a href="http://www.opensource.org/licenses/bsd-license.html">BSD-License</a>.
+    If you would like to use this CGI script on your own web server and
+    CVS tree, see Greg's
+    <a href="http://www.lyra.org/viewcvs/">ViewCVS distribution
+    site</a>.
+    Please send any suggestions, comments, etc. to
+    <a href="mailto:gstein@lyra.org">Greg Stein</a>.
+    </p>
+    """
+    # ' stupid emacs...
+
+    self.text.doc_info = """
+    <h3>CVS Documentation</h3>
+    <blockquote>
+    <p>
+      <a href="http://www.loria.fr/~molli/cvs/doc/cvs_toc.html">CVS
+      User's Guide</a><br>
+      <a href="http://www.arc.unm.edu/~rsahu/cvs.html">CVS Tutorial</a><br>
+      <a href="http://cellworks.washington.edu/pub/docs/cvs/tutorial/cvs_tutorial_1.html">Another CVS tutorial</a><br>
+      <a href="http://www.csc.calpoly.edu/~dbutler/tutorials/winter96/cvs/">Yet another CVS tutorial (a little old, but nice)</a><br>
+      <a href="http://www.cs.utah.edu/dept/old/texinfo/cvs/FAQ.txt">An old but very useful FAQ about CVS</a>
+    </p>
+    </blockquote>
+    """
+
+    # Fill in stuff on (say) anonymous pserver access here. For example, what
+    # access mechanism, login, path, etc should be used.
+    self.text.repository_info = """
+    <!-- insert repository access instructions here -->
+    """
+
+    self.text.short_intro = """\
+    <p>
+    Click on a directory to enter that directory. Click on a file to display
+    its revision history and to get a chance to display diffs between revisions. 
+    </p>
+    """
+
+class _sub_config:
+  def get_image(self, which):
+    text = '[%s]' % string.upper(which)
+    path, width, height = getattr(self, which)
+    if path:
+      return '<img src="%s" alt="%s" border=0 width=%s height=%s>' % \
+             (path, text, width, height)
+    return text

lib/cvsdbapi.py

@@ -0,0 +1,138 @@
+# -*- Mode: python -*-
+# -----------------------------------------------------------------------
+# Copyright (C) 2000 Jay Painter. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth below:
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
+#
+# -----------------------------------------------------------------------
+#
+# For tracking purposes, this software is identified by:
+#   $Id$
+#
+# -----------------------------------------------------------------------
+
+import os, cfg, database, rlog, commit
+
+## error
+error = 'cvsdbapi error'
+
+## database
+CreateCheckinDatabase = database.CreateCheckinDatabase
+CreateCheckinQuery = database.CreateCheckinQuery
+
+## rlog
+GetRLogData = rlog.GetRLogData
+
+## commit
+CreateCommit = commit.CreateCommit
+PrintCommit = commit.PrintCommit
+
+## cached (active) database connections
+gCheckinDatabase = None
+gCheckinDatabaseReadOnly = None
+
+
+def ConnectDatabaseReadOnly():
+    global gCheckinDatabaseReadOnly
+    
+    if gCheckinDatabaseReadOnly:
+        return gCheckinDatabaseReadOnly
+    
+    gCheckinDatabaseReadOnly = database.CreateCheckinDatabase(
+        cfg.cvsdb.host,
+        cfg.cvsdb.readonly_user,
+        cfg.cvsdb.readonly_passwd,
+        cfg.cvsdb.database_name)
+    
+    gCheckinDatabaseReadOnly.Connect()
+    return gCheckinDatabaseReadOnly
+
+
+def ConnectDatabase():
+    global gCheckinDatabase
+    
+    gCheckinDatabase = database.CreateCheckinDatabase(
+        cfg.cvsdb.host,
+        cfg.cvsdb.user,
+        cfg.cvsdb.passwd,
+        cfg.cvsdb.database_name)
+    
+    gCheckinDatabase.Connect()
+    return gCheckinDatabase
+
+
+def RLogDataToCommitList(repository, rlog_data):
+    commit_list = []
+
+    ## the filename in rlog_data contains the entire path of the
+    ## repository; we strip that out here
+    temp = rlog_data.filename[len(repository):]
+    directory, file = os.path.split(temp)
+
+    for rlog_entry in rlog_data.rlog_entry_list:
+        commit = CreateCommit()
+        commit.SetRepository(repository)
+        commit.SetDirectory(directory)
+        commit.SetFile(file)
+        commit.SetRevision(rlog_entry.revision)
+        commit.SetAuthor(rlog_entry.author)
+        commit.SetDescription(rlog_entry.description)
+        commit.SetTime(rlog_entry.time)
+        commit.SetPlusCount(rlog_entry.pluscount)
+        commit.SetMinusCount(rlog_entry.minuscount)
+        commit.SetBranch(rlog_data.LookupBranch(rlog_entry))
+
+        if rlog_entry.type == rlog_entry.CHANGE:
+            commit.SetTypeChange()
+        elif rlog_entry.type == rlog_entry.ADD:
+            commit.SetTypeAdd()
+        elif rlog_entry.type == rlog_entry.REMOVE:
+            commit.SetTypeRemove()
+
+        commit_list.append(commit)
+
+    return commit_list
+
+
+def GetCommitListFromRCSFile(repository, filename):
+    try:
+        rlog_data = GetRLogData(filename)
+    except rlog.error, e:
+        raise error, e
+    
+    commit_list = RLogDataToCommitList(repository, rlog_data)
+    return commit_list
+
+
+def GetUnrecordedCommitList(repository, filename):
+    commit_list = GetCommitListFromRCSFile(repository, filename)
+    db = ConnectDatabase()
+
+    unrecorded_commit_list = []
+    for commit in commit_list:
+        result = db.CheckCommit(commit)
+        if not result:
+            unrecorded_commit_list.append(commit)
+
+    return unrecorded_commit_list

lib/database.py

@@ -0,0 +1,495 @@
+# -*- Mode: python -*-
+# -----------------------------------------------------------------------
+# Copyright (C) 2000 Jay Painter. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth below:
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
+#
+# -----------------------------------------------------------------------
+#
+# For tracking purposes, this software is identified by:
+#   $Id$
+#
+# -----------------------------------------------------------------------
+
+import os, sys, string, time
+
+## imports from the database API; we re-assign the namespace here so it
+## is easier to switch databases
+import MySQLdb
+DBI = MySQLdb
+
+from commit import CreateCommit, PrintCommit
+
+
+## base strings used in SQL querries, these should be static members
+## of the CheckinDatabase class
+
+sqlBase = 'SELECT checkins.type, checkins.ci_when,checkins. whoid, checkins.repositoryid, checkins.dirid, checkins.fileid, checkins.revision, checkins.stickytag, checkins.branchid, checkins.addedlines, checkins.removedlines, checkins.descid FROM %s WHERE %s %s'
+sqlRepository = '(checkins.repositoryid=repositories.id AND repositories.repository="%s")'
+sqlBranch = '(checkins.branchid=branches.id AND branches.branch="%s")'
+sqlDirectory = '(checkins.dirid=dirs.id AND dirs.dir LIKE "%s%%")'         
+sqlFile = '(checkins.fileid=files.id AND files.file="%s")'
+sqlFromDate ='(checkins.ci_when>="%s")'
+sqlToDate = '(checkins.ci_when<="%s")'
+sqlAuthor = '(checkins.whoid=people.id AND people.who="%s")'
+sqlSortByDate = 'ORDER BY checkins.ci_when DESC'
+sqlSortByAuthor = 'ORDER BY checkins.whoid'
+sqlSortByFile = 'ORDER BY checkins.fileid'  
+sqlExcludeVersionFiles = '(checkins.fileid=files.id AND files.file NOT LIKE "%%.ver")'
+sqlCheckCommit = 'SELECT * FROM checkins WHERE checkins.repositoryid=%s AND checkins.dirid=%s AND checkins.fileid=%s AND checkins.revision=%s'
+
+## CheckinDatabase provides all interfaces needed to the SQL database
+## back-end; it needs to be subclassed, and have its "Connect" method
+## defined to actually be complete; it should run well off of any DBI 2.0
+## complient database interface
+
+class CheckinDatabase:
+    def __init__(self, host, user, passwd, database):
+        self.dbHost = host
+        self.dbUser = user
+        self.dbPasswd = passwd
+        self.dbDatabase = database
+
+        ## cache Value lookups
+        self.dbGetCache = {}
+        self.dbGetIDCache = {}
+        self.dbDescriptionIDCache = {}
+
+    def Connect(self):
+        self.dbConn = self.SQLConnect()
+
+    def SQLGetID(self, table, field, identifier, auto_set):
+        sql = 'SELECT id FROM %s x WHERE x.%s="%s"' % (
+            table, field, identifier)
+                
+        cursor = self.dbConn.cursor()
+        cursor.execute(sql)
+        row = cursor.fetchone()
+        if row:
+            return row[0]
+
+        if not auto_set:
+            return None
+
+        ## insert the new identifier
+        sql = 'INSERT INTO %s (%s) VALUES ("%s")' % (table, field, identifier)
+        cursor.execute(sql)
+        return self.SQLGetID(table, field, identifier, 0)
+
+    def GetID(self, table, field, identifier, auto_set):
+        ## attempt to retrieve from cache
+        try:
+            return self.dbGetIDCache[table][field][identifier]
+        except KeyError:
+            pass
+
+        id = self.SQLGetID(table, field, identifier, auto_set)
+        if not id:
+            return id
+
+        ## add to cache
+        if not self.dbGetIDCache.has_key(table):
+            self.dbGetIDCache[table] = {}
+        if not self.dbGetIDCache[table].has_key(field):
+            self.dbGetIDCache[table][field] = {}
+        self.dbGetIDCache[table][field][identifier] = id
+        return id
+
+    def SQLGet(self, table, field, id):
+        sql = 'SELECT %s FROM %s x WHERE x.id="%s"' % (field, table, id)
+                
+        cursor = self.dbConn.cursor()
+        cursor.execute(sql)
+        row = cursor.fetchone()
+        if not row:
+            return None
+        return row[0]
+
+    def Get(self, table, field, id):
+        ## attempt to retrieve from cache
+        try:
+            return self.dbGetCache[table][field][id]
+        except KeyError:
+            pass
+
+        value = self.SQLGet(table, field, id)
+        if not value:
+            return None
+
+        ## add to cache
+        if not self.dbGetCache.has_key(table):
+            self.dbGetCache[table] = {}
+        if not self.dbGetCache[table].has_key(field):
+            self.dbGetCache[table][field] = {}
+        self.dbGetCache[table][field][id] = value
+        return value
+
+    def GetBranchID(self, branch, auto_set = 1):
+        return self.GetID('branches', 'branch', branch, auto_set)
+
+    def GetBranch(self, id):
+        return self.Get('branches', 'branch', id)
+
+    def GetDirectoryID(self, dir, auto_set = 1):
+        return self.GetID('dirs', 'dir', dir, auto_set)
+
+    def GetDirectory(self, id):
+        return self.Get('dirs', 'dir', id)
+
+    def GetFileID(self, file, auto_set = 1):
+        return self.GetID('files', 'file', file, auto_set)
+
+    def GetFile(self, id):
+        return self.Get('files', 'file', id)
+    
+    def GetAuthorID(self, author, auto_set = 1):
+        return self.GetID('people', 'who', author, auto_set)
+
+    def GetAuthor(self, id):
+        return self.Get('people', 'who', id)
+    
+    def GetRepositoryID(self, repository, auto_set = 1):
+        return self.GetID('repositories', 'repository', repository, auto_set)
+
+    def GetRepository(self, id):
+        return self.Get('repositories', 'repository', id)
+
+    def SQLGetDescriptionID(self, description, auto_set = 1):
+        ## lame string hash, blame Netscape -JMP
+        hash = len(description)
+        
+        cursor = self.dbConn.cursor()
+        cursor.execute(
+            'SELECT id FROM descs WHERE hash=%s and description=%s',
+            (hash, description))
+
+        row = cursor.fetchone()
+        if row:
+            return row[0]
+
+        if not auto_set:
+            return None
+
+        cursor = self.dbConn.cursor()
+        cursor.execute(
+            'INSERT INTO descs (hash, description) values (%s, %s)',
+            (hash, description))
+        
+        return self.GetDescriptionID(description, 0)
+
+    def GetDescriptionID(self, description, auto_set = 1):
+        ## lame string hash, blame Netscape -JMP
+        hash = len(description)
+        
+        ## attempt to retrieve from cache
+        try:
+            return self.dbDescriptionIDCache[hash][description]
+        except KeyError:
+            pass
+
+        id = self.SQLGetDescriptionID(description, auto_set)
+        if not id:
+            return id
+
+        ## add to cache
+        if not self.dbDescriptionIDCache.has_key(hash):
+            self.dbDescriptionIDCache[hash] = {}
+        self.dbDescriptionIDCache[hash][description] = id
+        return id
+
+    def GetDescription(self, id):
+        return self.Get('descs', 'description', id)
+
+    def GetList(self, table, field_index):
+        sql = 'SELECT * FROM %s' % (table)
+        
+        cursor = self.dbConn.cursor()
+        cursor.execute(sql)
+
+        list = []
+        while 1:
+            row = cursor.fetchone()
+            if not row:
+                break
+            list.append(row[field_index])
+
+        return list
+
+    def GetRepositoryList(self):
+        return self.GetList('repositories', 1)
+
+    def GetBranchList(self):
+        return self.GetList('branches', 1)
+
+    def GetAuthorList(self):
+        return self.GetList('people', 1)
+
+    def AddCommitList(self, commit_list):
+        for commit in commit_list:
+            self.AddCommit(commit)
+
+    def AddCommit(self, commit):
+        dbType = commit.GetTypeString()
+
+        ## MORE TIME HELL: the MySQLdb module doesn't construct times
+        ## correctly when created with TimestampFromTicks -- it doesn't
+        ## account for daylight savings time, so we use Python's time
+        ## module to do the conversion
+        temp = time.localtime(commit.GetTime())
+
+        dbCI_When = DBI.Timestamp(
+            temp[0], temp[1], temp[2], temp[3], temp[4], temp[5])
+        
+        dbWhoID = self.GetAuthorID(commit.GetAuthor())
+        dbRepositoryID = self.GetRepositoryID(commit.GetRepository())
+        dbDirectoryID = self.GetDirectoryID(commit.GetDirectory())
+        dbFileID = self.GetFileID(commit.GetFile())
+        dbRevision = commit.GetRevision()
+        dbStickyTag = 'NULL'
+        dbBranchID = self.GetBranchID(commit.GetBranch())
+        dbPlusCount = commit.GetPlusCount()
+        dbMinusCount = commit.GetMinusCount()
+        dbDescriptionID = self.GetDescriptionID(commit.GetDescription())
+        
+        sql = 'REPLACE INTO checkins(type, ci_when, whoid, repositoryid, dirid, fileid, revision, stickytag, branchid, addedlines, removedlines, descid) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)'
+        sqlArguments = (
+            dbType, dbCI_When, dbWhoID, dbRepositoryID, dbDirectoryID,
+            dbFileID, dbRevision, dbStickyTag, dbBranchID, dbPlusCount,
+            dbMinusCount, dbDescriptionID)
+
+        cursor = self.dbConn.cursor()
+        cursor.execute(sql, sqlArguments)
+
+    def CreateSQLQueryString(self, query):
+        tableList = ['checkins']
+        condList = []
+   
+        tableList.append('files')
+        condList.append(sqlExcludeVersionFiles)
+ 
+        if query.repository:
+            tableList.append('repositories')
+            condList.append(sqlRepository % (query.repository))
+
+        if query.branch:
+            tableList.append('branches')
+            condList.append(sqlBranch % (query.branch))
+
+        if query.from_date:
+            condList.append(sqlFromDate % (str(query.from_date)))
+
+        if query.to_date:
+            condList.append(sqlToDate % (str(query.to_date)))
+
+        if query.author:
+            tableList.append('people')
+            condList.append(sqlAuthor % (query.author))
+
+        if query.directory:
+            tableList.append('dirs')
+            condList.append(sqlDirectory % (query.directory))
+
+        if query.file:
+            #tableList.append('files')
+            condList.append(sqlFile % (query.file))
+
+        if query.sort == query.SORT_DATE:
+            order_by = sqlSortByDate
+        elif query.sort == query.SORT_AUTHOR:
+            order_by = sqlSortByAuthor
+        elif query.sort == query.SORT_FILE:
+            order_by = sqlSortByFile
+
+        sql = sqlBase % (
+            string.join(tableList, ', '),
+            string.join(condList, ' AND '),
+            order_by)
+
+        return sql
+    
+    def RunQuery(self, query):
+        sql = self.CreateSQLQueryString(query)
+        cursor = self.dbConn.cursor()
+        cursor.execute(sql)
+        
+        while 1:
+            row = cursor.fetchone()
+            if not row:
+                break
+            
+            (dbType, dbCI_When, dbAuthorID, dbRepositoryID, dbDirID,
+             dbFileID, dbRevision, dbStickyTag, dbBranchID, dbAddedLines,
+             dbRemovedLines, dbDescID) = row
+
+            commit = CreateCommit()
+
+            ## TIME, TIME, TIME is all fucked up; dateobject.gmticks()
+            ## is broken, dateobject.ticks() returns somthing like
+            ## GMT ticks, except it forgets about daylight savings
+            ## time -- we handle it ourself in the following painful way
+            gmt_time = time.mktime(
+                (dbCI_When.year, dbCI_When.month, dbCI_When.day,
+                 dbCI_When.hour, dbCI_When.minute, dbCI_When.second,
+                 0, 0, dbCI_When.dst))
+    
+            commit.SetTime(gmt_time)
+            
+            commit.SetFile(self.GetFile(dbFileID))
+            commit.SetDirectory(self.GetDirectory(dbDirID))
+            commit.SetRevision(dbRevision)
+            commit.SetRepository(self.GetRepository(dbRepositoryID))
+            commit.SetAuthor(self.GetAuthor(dbAuthorID))
+            commit.SetBranch(self.GetBranch(dbBranchID))
+            commit.SetPlusCount(dbAddedLines)
+            commit.SetMinusCount(dbRemovedLines)
+            commit.SetDescription(self.GetDescription(dbDescID))
+
+            query.AddCommit(commit)
+
+    def CheckCommit(self, commit):
+        dbRepositoryID = self.GetRepositoryID(commit.GetRepository(), 0)
+        if dbRepositoryID == None:
+            return None
+
+        dbDirID = self.GetDirectoryID(commit.GetDirectory(), 0)
+        if dbDirID == None:
+            return None
+
+        dbFileID = self.GetFileID(commit.GetFile(), 0)
+        if dbFileID == None:
+            return None
+
+        sqlArguments = (dbRepositoryID, dbDirID, dbFileID,
+                        commit.GetRevision())
+
+        cursor = self.dbConn.cursor()
+        cursor.execute(sqlCheckCommit, sqlArguments)
+        row = cursor.fetchone()
+        if not row:
+            return None
+
+        return commit
+        
+
+class MySQLCheckinDatabase(CheckinDatabase):
+    def SQLConnect(self):
+        return MySQLdb.connect(
+            host = self.dbHost,
+            user = self.dbUser,
+            passwd = self.dbPasswd,
+            db = self.dbDatabase)
+
+
+## CheckinDatabaseQueryData is a object which contains the search parameters
+## for a query to the CheckinDatabase
+
+class CheckinDatabaseQuery:
+
+    SORT_DATE = 0
+    SORT_AUTHOR = 1
+    SORT_FILE = 2
+    SORT_CHANGESIZE = 3
+    
+    def __init__(self):
+        ## repository to query
+        self.repository = None
+
+        ## branch
+        self.branch = None
+
+        ## directory to seach
+        self.directory = None
+
+        ## file to search for
+        self.file = None
+
+        ## sorting method
+        self.sort = CheckinDatabaseQuery.SORT_DATE;
+        
+        ## author to search for
+        self.author = None
+
+        ## date range in DBI 2.0 timedate objects
+        self.from_date = None
+        self.to_date = None
+
+        ## list of commits -- filled in by CVS query
+        self.commit_list = []
+
+        ## commit_cb provides a callback for commits as they
+        ## are added
+        self.commit_cb = None
+
+    def SetRepository(self, repository):
+        self.repository = repository
+
+    def SetBranch(self, branch):
+        self.branch = branch
+
+    def SetDirectory(self, directory):
+        self.directory = directory
+
+    def SetFile(self, file):
+        self.file = file
+
+    def SetSortMethod(self, sort):
+        self.sort = sort
+
+    def SetAuthor(self, author):
+        self.author = author
+
+    def SetFromDateObject(self, date):
+        self.from_date = date
+
+    def SetToDateObject(self, date):
+        self.to_date = date
+
+    def SetFromDateHoursAgo(self, hours_ago):
+        ticks = time.time() - (3600 * hours_ago)
+        self.from_date = DBI.TimestampFromTicks(ticks)
+        
+    def SetFromDateDaysAgo(self, days_ago):
+        ticks = time.time() - (86400 * days_ago)
+        self.from_date = DBI.TimestampFromTicks(ticks)
+
+    def SetToDateDaysAgo(self, days_ago):
+        ticks = time.time() - (86400 * days_ago)
+        self.to_date = DBI.TimestampFromTicks(ticks)
+
+    def AddCommit(self, commit):
+        self.commit_list.append(commit)
+        if self.commit_cb:
+            self.commit_cb(commit)
+        
+    def SetCommitCB(self, callback):
+        self.commit_cb = callback
+        
+
+## entrypoints
+
+def CreateCheckinDatabase(host, user, passwd, database):
+    return MySQLCheckinDatabase(host, user, passwd, database)
+
+def CreateCheckinQuery():
+    return CheckinDatabaseQuery()

lib/py2html.py

@@ -0,0 +1,489 @@
+#!/usr/local/bin/python -u
+
+""" Python Highlighter for HTML                          Version: 0.5
+
+    py2html.py [options] files...
+
+    options:
+     -h             print help
+     -              read from stdin, write to stdout
+     -stdout        read from files, write to stdout
+     -files         read from files, write to filename+'.html' (default)
+     -format:
+       html         output HTML page (default)
+       rawhtml      output pure HTML (without headers, titles, etc.)
+     -mode:
+       color        output in color (default)
+       mono         output b/w (for printing)
+     -title:Title   use 'Title' as title of the generated page
+     -bgcolor:color use color as background-color for page
+     -header:file   use contents of file as header
+     -footer:file   use contents of file as footer
+     -URL           replace all occurances of 'URL: link' with
+                    '<A HREF="link">link</A>'; this is always enabled
+		    in CGI mode
+     -v             verbose
+
+    Takes the input, assuming it is Python code and formats it into
+    colored HTML. When called without parameters the script tries to
+    work in CGI mode. It looks for a field 'script=URL' and tries to
+    use that URL as input file. If it can't find this field, the path
+    info (the part of the URL following the CGI script name) is
+    tried. In case no host is given, the host where the CGI script
+    lives and HTTP are used.
+ 
+    * Uses Just van Rossum's PyFontify version 0.3 to tag Python scripts.
+      You can get it via his homepage on starship:
+        URL: http://starship.skyport.net/crew/just
+"""
+__comments__ = """
+
+    The following snippet is a small shell script I use for viewing
+    Python scripts per less on Unix:
+#!/bin/sh
+# Browse pretty printed Python code using ANSI codes for highlighting
+py2html -stdout -format:ansi -mode:mono $* | less -r
+
+    History:
+	
+    0.5: Added a few suggestions by Kevin Ng to make the CGI version
+         a little more robust.
+
+"""
+__copyright__ = """
+-----------------------------------------------------------------------------
+(c) Copyright by Marc-Andre Lemburg, 1998 (mailto:mal@lemburg.com)
+
+    Permission to use, copy, modify, and distribute this software and its
+    documentation for any purpose and without fee or royalty is hereby granted,
+    provided that the above copyright notice appear in all copies and that
+    both that copyright notice and this permission notice appear in
+    supporting documentation or portions thereof, including modifications,
+    that you make.
+
+    THE AUTHOR MARC-ANDRE LEMBURG DISCLAIMS ALL WARRANTIES WITH REGARD TO
+    THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
+    FITNESS, IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL,
+    INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING
+    FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
+    NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION
+    WITH THE USE OR PERFORMANCE OF THIS SOFTWARE !
+"""
+
+__version__ = '0.5'
+
+__cgifooter__ = ('\n<PRE># code highlighted using <A HREF='
+		 '"http://starship.skyport.net/~lemburg/">py2html.py</A> '
+		 'version %s</PRE>\n' % __version__)
+
+import sys,string,re
+
+# Adjust path so that PyFontify is found...
+sys.path.append('.')
+
+### Constants
+
+# URL of the input form the user is redirected to in case no script=xxx
+# form field is given. The URL *must* be absolute. Leave blank to
+# have the script issue an error instead.
+INPUT_FORM = 'http://starship.skyport.net/~lemburg/SoftwareDescriptions.html#py2html.py'
+
+### Helpers
+
+def fileio(file, mode='rb', data=None, close=0):
+
+    if type(file) == type(''):
+	f = open(file,mode)
+	close = 1
+    else:
+	f = file
+    if data:
+	f.write(data)
+    else:
+	data = f.read()
+    if close: f.close()
+    return data
+
+### Converter class
+
+class PrettyPrint:
+
+    """ generic Pretty Printer class
+
+        * supports tagging Python scripts in the following ways: 
+
+	  # format/mode |  color  mono
+	  # --------------------------
+	  # rawhtml     |    x     x   (HTML without headers, etc.)
+	  # html        |    x     x   (a HTML page with HEAD&BODY:)
+	  # ansi        |          x   (with Ansi-escape sequences)
+
+	* interfaces:
+
+	   file_filter -- takes two files: input & output (may be stdin/stdout)
+	   filter -- takes a string and returns the highlighted version
+	
+	* to create an instance use:
+
+	  c = PrettyPrint(tagfct,format,mode)
+
+	  where format and mode must be strings according to the
+	  above table if you plan to use PyFontify.fontify as
+	  tagfct
+
+        * the tagfct has to take one argument, text, and return a taglist
+	  (format: [(id,left,right,sublist),...], where id is the
+	  "name" given to the slice left:right in text and sublist is a
+	  taglist for tags inside the slice or None)
+
+    """
+
+    # misc settings
+    title = ''
+    bgcolor = '#FFFFFF'
+    header = ''
+    footer = ''
+    replace_URLs = 0
+    # formats to be used
+    formats = {}
+
+    def __init__(self,tagfct=None,format='html',mode='color'):
+
+	self.tag = tagfct
+	self.set_mode = getattr(self,'set_mode_'+format+'_'+mode)
+	self.filter = getattr(self,'filter_'+format)
+	self.set_mode()
+
+    def file_filter(self,infile,outfile):
+
+	text = fileio(infile,'r')
+	if type(infile) == type('') and self.title == '':
+	    self.title = infile
+	fileio(outfile,'w',self.filter(text))
+
+    ### set pre- and postfixes for formats & modes
+    #
+    # These methods must set self.formats to a dictionary having
+    # an entry for every tag returned by the tagging function.
+    #
+    # The format used is simple:
+    #  tag:(prefix,postfix)
+    # where prefix and postfix are either strings or callable objects,
+    # that return a string (they are called with the matching tag text
+    # as only parameter). prefix is inserted in front of the tag, postfix
+    # is inserted right after the tag.
+
+    def set_mode_html_color(self):
+
+	self.formats = {
+	    'all':('<PRE>','</PRE>'),
+	    'comment':('<FONT COLOR=#1111CC>','</FONT>'),
+	    'keyword':('<FONT COLOR=#3333CC><B>','</B></FONT>'),
+	    'parameter':('<FONT COLOR=#000066>','</FONT>'),
+	    'identifier':( lambda x,strip=string.strip:
+                           '<A NAME="%s"><FONT COLOR=#CC0000><B>' % (strip(x)),
+	                   '</B></FONT></A>'),
+	    'string':('<FONT COLOR=#115511>','</FONT>')
+	    }
+
+    set_mode_rawhtml_color = set_mode_html_color
+
+    def set_mode_html_mono(self):
+
+	self.formats = {
+	    'all':('<PRE>','</PRE>'),
+	    'comment':('',''),
+	    'keyword':( '<U>','</U>'),
+	    'parameter':('',''),
+	    'identifier':( lambda x,strip=string.strip:
+                           '<A NAME="%s"><B>' % (strip(x)),
+		           '</B>'),
+	    'string':('','')
+	    }
+
+    set_mode_rawhtml_mono = set_mode_html_mono
+
+    def set_mode_ansi_mono(self):
+
+	self.formats = {
+	    'all':('',''),
+	    'comment':('\033[2m','\033[m'),
+	    'keyword':('\033[4m','\033[m'),
+	    'parameter':('',''),
+	    'identifier':('\033[1m','\033[m'),
+	    'string':('','')
+	    }
+
+    ### filter for Python scripts given as string
+
+    def escape_html(self,text):
+
+	t = (('<','&lt;'),('>','&gt;'))
+	for x,y in t:
+	    text = string.join(string.split(text,x),y)
+	return text
+
+    def filter_html(self,text):
+
+	output = self.fontify(self.escape_html(text))
+	if self.replace_URLs: 
+	    output = re.sub('URL:([ \t]+)([^ \n\r<]+)',
+			    'URL:\\1<A HREF="\\2">\\2</A>',output)
+	html = """<HTML><HEAD><TITLE>%s</TITLE></HEAD>
+		  <BODY BGCOLOR=%s>
+		  <!--header-->%s
+		  <!--script-->%s
+		  <!--footer-->%s
+		  </BODY>\n"""%(self.title,self.bgcolor,self.header,output,self.footer)
+	return html
+
+    def filter_rawhtml(self,text):
+
+	output = self.fontify(self.escape_html(text))
+	if self.replace_URLs: 
+	    output = re.sub('URL:([ \t]+)([^ \n\r<]+)',
+			    'URL:\\1<A HREF="\\2">\\2</A>',output)
+	return self.header+output+self.footer
+
+    def filter_ansi(self,text):
+
+	output = self.fontify(text)
+	return self.header+output+self.footer
+
+    ### fontify engine
+
+    def fontify(self,pytext):
+
+	# parse
+	taglist = self.tag(pytext)
+
+	# prepend special 'all' tag:
+	taglist[:0] = [('all',0,len(pytext),None)]
+
+	# prepare splitting
+	splits = []
+	addsplits(splits,pytext,self.formats,taglist)
+
+	# do splitting & inserting
+	splits.sort()
+	l = []
+	li = 0
+	for ri,dummy,insert in splits:
+	    if ri > li: l.append(pytext[li:ri])
+	    l.append(insert)
+	    li = ri
+	if li < len(pytext): l.append(pytext[li:])
+	
+	return string.join(l,'')
+
+def addsplits(splits,text,formats,taglist):
+    # helper for fontify()
+    for id,left,right,sublist in taglist:
+	try:
+	    pre,post = formats[id]
+	except KeyError:
+	    # sys.stderr.write('Warning: no format for %s specified\n'%repr(id))
+	    pre,post = '',''
+	if type(pre) != type(''):
+	    pre = pre(text[left:right])
+	if type(post) != type(''):
+	    post = post(text[left:right])
+	# len(splits) is a dummy used to make sorting stable
+	splits.append((left,len(splits),pre))
+	if sublist:
+	    addsplits(splits,text,formats,sublist)
+	splits.append((right,len(splits),post))
+
+def write_html_error(titel,text):
+
+    print """\
+<HTML><HEADER><TITLE>%s</TITLE></HEADER>
+<BODY>
+<H2>%s</H2>
+%s
+</BODY></HTML>
+""" % (titel,titel,text)
+
+def redirect_to(url):
+
+    sys.stdout.write('Content-Type: text/html\r\n')
+    sys.stdout.write('Status: 302\r\n')
+    sys.stdout.write('Location: %s\r\n\r\n' % url)
+    print """
+<HTML><HEAD>
+<TITLE>302 Moved Temporarily</TITLE>
+</HEAD><BODY>
+<H1>302 Moved Temporarily</H1>
+The document has moved to <A HREF="%s">%s</A>.<P>
+</BODY></HTML>
+""" % (url,url)
+
+def main(cmdline):
+
+    """ main(cmdline) -- process cmdline as if it were sys.argv 
+    """
+    # parse options/files
+    options = []
+    optvalues = {}
+    for o in cmdline[1:]:
+	if o[0] == '-':
+	    if ':' in o:
+		k,v = tuple(string.split(o,':'))
+		optvalues[k] = v
+		options.append(k)
+	    else:
+		options.append(o)
+	else:
+	    break
+    files = cmdline[len(options)+1:]
+
+    # create converting object	
+
+    # load fontifier
+    if '-marcs' in options:
+	# use mxTextTool's tagging engine
+	from mxTextTools import tag
+	from mxTextTools.Examples.Python import python_script
+	tagfct = lambda text,tag=tag,pytable=python_script: \
+		 tag(text,pytable)[1]
+	print "Py2HTML: using Marc's tagging engine"
+    else:
+	# load Just's
+	try:
+	    import PyFontify
+	    if PyFontify.__version__ < '0.3': raise ValueError
+	    tagfct = PyFontify.fontify
+	except:
+	    print """
+    Sorry, but this script needs the PyFontify.py module version 0.3;
+    You can download it from Just's homepage at
+
+       URL: http://starship.skyport.net/crew/just
+"""
+	    sys.exit()
+	
+
+    if '-format' in options:
+	format = optvalues['-format']
+    else:
+	# use default
+	format = 'html'
+
+    if '-mode' in options:
+	mode = optvalues['-mode']
+    else:
+	# use default
+	mode = 'color'
+
+    c = PrettyPrint(tagfct,format,mode)
+    convert = c.file_filter
+
+    # start working
+
+    if '-title' in options:
+	c.title = optvalues['-title']
+
+    if '-bgcolor' in options:
+	c.bgcolor = optvalues['-bgcolor']
+
+    if '-header' in options:
+	try:
+	    f = open(optvalues['-header'])
+	    c.header = f.read()
+	    f.close()
+	except IOError:
+	    if verbose: print 'IOError: header file not found'
+	    
+    if '-footer' in options:
+	try:
+	    f = open(optvalues['-footer'])
+	    c.footer = f.read()
+	    f.close()
+	except IOError:
+	    if verbose: print 'IOError: footer file not found'
+
+    if '-URL' in options:
+	c.replace_URLs = 1
+
+    if '-' in options:
+	convert(sys.stdin,sys.stdout)
+	sys.exit()
+
+    if '-h' in options:
+	print __doc__
+	sys.exit()
+
+    if len(files) == 0:
+	# Turn URL processing on
+	c.replace_URLs = 1
+	# Try CGI processing...
+	import cgi,urllib,urlparse,os
+	form = cgi.FieldStorage()
+	if not form.has_key('script'):
+	    # Ok, then try pathinfo
+	    if not os.environ.has_key('PATH_INFO'):
+		if INPUT_FORM:
+		    redirect_to(INPUT_FORM)
+		else:
+		    sys.stdout.write('Content-Type: text/html\r\n\r\n')
+		    write_html_error('Missing Parameter',
+				     'Missing script=URL field in request')
+		sys.exit(1)
+	    url = os.environ['PATH_INFO'][1:] # skip the leading slash
+	else:
+	    url = form['script'].value
+	sys.stdout.write('Content-Type: text/html\r\n\r\n')
+	scheme, host, path, params, query, frag = urlparse.urlparse(url)
+	if not host:
+	    scheme = 'http'
+	    if os.environ.has_key('HTTP_HOST'):
+		host = os.environ['HTTP_HOST']
+	    else:
+		host = 'localhost'
+	    url = urlparse.urlunparse((scheme, host, path, params, query, frag))
+	#print url; sys.exit()
+	network = urllib.URLopener()
+	try:
+	    tempfile,headers = network.retrieve(url)
+	except IOError,reason:
+	    write_html_error('Error opening "%s"' % url,
+			     'The given URL could not be opened. Reason: %s' %\
+			     str(reason))
+	    sys.exit(1)
+	f = open(tempfile,'rb')
+	c.title = url
+	c.footer = __cgifooter__
+	convert(f,sys.stdout)
+	f.close()
+	network.close()
+	sys.exit()
+
+    if '-stdout' in options:
+	filebreak = '-'*72
+	for f in files:
+	    try:
+		if len(files) > 1:
+		    print filebreak
+		    print 'File:',f
+		    print filebreak
+		convert(f,sys.stdout)
+	    except IOError:
+		pass
+    else:
+	verbose = ('-v' in options)
+	if verbose:
+	    print 'Py2HTML: working on',
+	for f in files:
+	    try:
+		if verbose: print f,
+		convert(f,f+'.html')
+	    except IOError:
+		if verbose: print '(IOError!)',
+	if verbose:
+	    print
+	    print 'Done.'
+
+if __name__=='__main__':
+    main(sys.argv)
+
+

lib/rlog.py

@@ -0,0 +1,348 @@
+# -*- Mode: python -*-
+# -----------------------------------------------------------------------
+# Copyright (C) 2000 Jay Painter. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth below:
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
+#
+# -----------------------------------------------------------------------
+#
+# For tracking purposes, this software is identified by:
+#   $Id$
+#
+# -----------------------------------------------------------------------
+
+import os, sys, string, time, re
+
+## RLogOutputParser uses the output of rlog to build a list of Commit
+## objects describing all the checkins from a given RCS file; this
+## parser is fairly optimized, and therefore can be delicate if the
+## rlog output varies between versions of rlog; I don't know if it does;
+## to make really fast, I should wrap the C rcslib
+
+## there's definately not much error checking here; I'll assume things
+## will go smoothly, and trap errors via exception handlers above this
+## function
+
+## exception for this class
+error = 'rlog error'
+
+
+class RLogData:
+    "Container object for all data parsed from a 'rlog' output."
+  
+    def __init__(self, filename):
+        self.filename = filename
+        self.symbolic_name_hash = {}
+        self.rlog_entry_list = []
+
+    def LookupBranch(self, rlog_entry):
+        index = string.rfind(rlog_entry.revision, '.')
+        branch_revision = rlog_entry.revision[:index]
+
+        try:
+            branch = self.symbolic_name_hash[branch_revision]
+        except KeyError:
+            branch = ''
+
+        return branch
+    
+
+class RLogEntry:
+    ## static constants for type of log entry; this will be changed
+    ## to strings I guess -JMP
+    CHANGE = 0
+    ADD = 1
+    REMOVE = 2
+
+## Here's the init function, which isn't needed since this class
+## is fully initalized by RLogParser when creating a new log entry.
+## Let's keep this initializer as a description of what is held in
+## the class, but keep it commented out since it only makes things
+## slow.
+##
+##     def __init__(self):
+##         self.revision = ''
+##         self.author = ''
+##         self.branch = ''
+##         self.pluscount = ''
+##         self.minuscount = ''
+##         self.description = ''
+##         self.time = None
+##         self.type = RLogEntry.CHANGE
+
+
+class RLog:
+    "Provides a alternative file-like interface for running 'rlog'."
+    
+    def __init__(self, filename, revision, date):
+        self.filename = self.fix_filename(filename)
+        self.checkout_filename = self.create_checkout_filename(self.filename)
+        self.revision = revision
+        self.date = date
+
+        arg_list = []
+        if self.revision:
+            arg_list.append('-r%s' % (self.revision))
+        if self.date:
+            arg_list.append('-d%s' % (self.date))
+
+        self.cmd = 'rlog %s "%s"' % (string.join(arg_list), self.filename)
+        self.rlog = os.popen(self.cmd, 'r')
+
+    def fix_filename(self, filename):
+        ## all RCS files have the ",v" ending
+        if filename[-2:] != ",v":
+            filename = "%s,v" % (filename)
+
+        if os.path.isfile(filename):
+            return filename
+
+        ## check the Attic for the RCS file
+        path, basename = os.path.split(filename)
+        filename = os.path.join(path, "Attic", basename)
+
+        if os.path.isfile(filename):
+            return filename
+        
+        raise error, "rlog file not found: %s" % (filename)
+
+    def create_checkout_filename(self, filename):
+        ## cut off the ",v"
+        checkout_filename = filename[:-2]
+
+        ## check if the file is in the Attic
+        path, basename = os.path.split(checkout_filename)
+        if path[-6:] != '/Attic':
+            return checkout_filename
+
+        ## remove the "Attic" part of the path
+        checkout_filename = os.path.join(path[:-6], basename)
+        return checkout_filename
+        
+    def readline(self):
+        try:
+            line = self.rlog.readline()
+        except AttributeError:
+            self.error()
+            
+        if line:
+            return line
+
+        status = self.close()
+        if status:
+            self.error()
+
+        return None
+
+    def close(self):
+        status = self.rlog.close()
+        self.rlog = None
+        return status
+
+
+    def error(self):
+        raise error, "unexpected rlog exit: %s" % (self.cmd)
+
+
+## constants used in the output parser
+
+_rlog_commit_sep = '----------------------------\n'
+_rlog_end = '=============================================================================\n'
+
+## regular expression used in the output parser
+_re_symbolic_name = re.compile("\s+([^:]+):\s+(.+)$")
+
+_re_revision = re.compile("^revision\s+([0-9.]+).*")
+
+_re_data_line = re.compile(
+    "^date:\s+(\d+)/(\d+)/(\d+)\s+(\d+):(\d+):(\d+);\s+"\
+    "author:\s+([^;]+);\s+"\
+    "state:\s+([^;]+);\s+"\
+    "lines:\s+\+(\d+)\s+\-(\d+)$")
+
+_re_data_line_add = re.compile(
+    "^date:\s+(\d+)/(\d+)/(\d+)\s+(\d+):(\d+):(\d+);\s+"\
+    "author:\s+([^;]+);\s+"\
+    "state:\s+([^;]+);$")
+
+class RLogOutputParser:
+    
+    def __init__(self, rlog):
+        self.rlog = rlog
+        self.rlog_data = RLogData(rlog.checkout_filename)
+
+        ## run the parser
+        self.parse_to_symbolic_names()
+        self.parse_symbolic_names()
+        self.parse_to_description()
+        self.parse_rlog_entries()
+    
+    def parse_to_symbolic_names(self):
+        while 1:
+            line = self.rlog.readline()
+            if line[:15] == 'symbolic names:':
+                break
+
+    def parse_symbolic_names(self):
+        ## parse all the tags int the branch_hash, it's used later to get
+        ## the text names of non-head branches
+        while 1:
+            line = self.rlog.readline()
+            match = _re_symbolic_name.match(line)
+            if not match:
+                break
+
+            (tag, revision) = match.groups()
+
+            ## check if the tag represents a branch, in RCS this means
+            ## the second-to-last number is a zero
+            index = string.rfind(revision, '.')
+            if revision[index-2:index] == '.0':
+                revision = revision[:index-2] + revision[index:]
+            
+            self.rlog_data.symbolic_name_hash[revision] = tag
+
+    def parse_to_description(self):
+        while 1:
+            line = self.rlog.readline()
+            if line[:12] == 'description:':
+                break
+            
+        ## eat all lines until we reach '-----' seperator
+        while 1:
+            line = self.rlog.readline()
+            if line == _rlog_commit_sep:
+                break
+
+    def parse_rlog_entries(self):
+        while 1:
+            rlog_entry = self.parse_one_rlog_entry()
+            if not rlog_entry:
+                break
+            self.rlog_data.rlog_entry_list.append(rlog_entry)
+
+    def parse_one_rlog_entry(self):
+        ## revision line/first line
+        line = self.rlog.readline()
+        if not line:
+            return None
+
+        ## revision
+        match = _re_revision.match(line)
+        (revision,) = match.groups()
+
+        ## data line
+        line = self.rlog.readline()
+        match = _re_data_line.match(line)
+        if not match:
+            match = _re_data_line_add.match(line)
+
+        if not match:
+            raise error, "bad rlog parser, no cookie!"
+
+        ## retrieve the matched grops as a tuple in hopes
+        ## this will be faster (ala profiler)
+        groups = match.groups()
+
+        year = string.atoi(groups[0])
+        month = string.atoi(groups[1])
+        day = string.atoi(groups[2])
+        hour = string.atoi(groups[3])
+        minute = string.atoi(groups[4])
+        second = string.atoi(groups[5])
+        author = groups[6]
+        state = groups[7]
+
+        ## very strange; here's the deal: if this is a newly added file,
+        ## then there is no plus/minus count count of lines; if there
+        ## is, then this could be a "CHANGE" or "REMOVE", you can tell
+        ## if the file has been removed by looking if state == 'dead'
+        try:
+            pluscount = groups[8]
+            minuscount = groups[9]
+        except IndexError:
+            pluscount = ''
+            minuscount = ''
+            cmit_type = RLogEntry.ADD
+        else:
+            if state == 'dead':
+                cmit_type = RLogEntry.REMOVE
+            else:
+                cmit_type = RLogEntry.CHANGE
+        
+        ## branch line: pretty much ignored if it's there
+        desc_line_list = []
+                
+        line = self.rlog.readline()
+        if not line[:10] == 'branches: ':
+            desc_line_list.append(string.rstrip(line))
+
+        ## suck up description
+        while 1:
+            line = self.rlog.readline()
+
+            ## the last line printed out by rlog is '===='...
+            ## or '------'... between entries
+            if line == _rlog_commit_sep or line == _rlog_end:
+                break
+
+            ## append line to the descripton list
+            desc_line_list.append(string.rstrip(line))
+
+        ## compute time using time routines in seconds from epoc GMT
+        ## NOTE: mktime's arguments are in local time, and we have
+        ##       them in GMT from RCS; therefore, we have to manually
+        ##       subtract out the timezone correction
+        ##
+        ## XXX: Linux glib2.0.7 bug: it looks like mktime doesn't honor
+        ##      the '0' flag to force no timezone correction, so we look
+        ##      at the correction ourself and do the right thing after
+        ##      mktime mangles the date
+        gmt_time = \
+            time.mktime((year, month, day, hour, minute, second, 0, 0, -1))
+
+        if time.daylight:
+            gmt_time = gmt_time - time.altzone
+        else:
+            gmt_time = gmt_time - time.timezone
+
+        ## now create and return the RLogEntry
+        rlog_entry = RLogEntry()
+        rlog_entry.type = cmit_type
+        rlog_entry.revision = revision
+        rlog_entry.author = author
+        rlog_entry.description = string.join(desc_line_list, '\n')
+        rlog_entry.time = gmt_time
+        rlog_entry.pluscount = pluscount
+        rlog_entry.minuscount = minuscount
+
+        return rlog_entry
+
+
+## entrypoints
+
+def GetRLogData(path, revision = '', date = ''):
+    rlog = RLog(path, revision, date)
+    rlog_parser = RLogOutputParser(rlog)
+    return rlog_parser.rlog_data

tools/cvsdbadmin

@@ -0,0 +1,164 @@
+#!/usr/bin/env python
+# -*- Mode: python -*-
+#
+# administrative program for CVSdb; this is primarily
+# used to add/rebuild CVS repositories to the database
+#
+# -----------------------------------------------------------------------
+# Copyright (C) 2000 Jay Painter. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth below:
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
+#
+# -----------------------------------------------------------------------
+#
+# For tracking purposes, this software is identified by:
+#   $Id$
+#
+# -----------------------------------------------------------------------
+
+## BOOTSTRAP
+import sys, os, string
+_viewcvs_root = string.strip(open("/etc/viewcvs/root", "r").read())
+sys.path.append(os.path.join(_viewcvs_root, "lib"))
+##
+
+import cvsdbapi
+
+
+def UpdateFile(db, repository, path):
+    try:
+        commit_list = cvsdbapi.GetUnrecordedCommitList(repository, path)
+    except cvsdbapi.error, e:
+        print '[ERROR] %s' % (e)
+        return
+
+    print '[%s[%d new commits]]' % (path, len(commit_list)),
+
+    ## add the commits into the database
+    for commit in commit_list:
+        db.AddCommit(commit)
+        sys.stdout.write('.')
+        sys.stdout.flush()
+    print
+
+
+def RecurseUpdate(db, repository, directory):
+    for path in os.listdir(directory):
+        path = os.path.join(directory, path)
+
+        if os.path.islink(path):
+            continue
+        
+        if os.path.isdir(path):
+            RecurseUpdate(db, repository, path)
+            continue
+        
+        if os.path.isfile(path):
+            if path[-2:] == ',v':
+                UpdateFile(db, repository, path)
+        
+
+def CommandUpdate():
+    ## connect to the database we are updating
+    db = cvsdbapi.ConnectDatabase()
+    repository = sys.argv[2]
+    RecurseUpdate(db, repository, repository)
+
+
+def RebuildFile(db, repository, path):
+    try:
+        commit_list = cvsdbapi.GetCommitListFromRCSFile(repository, path)
+    except cvsdbapi.error, e:
+        print '[ERROR] %s' % (e)
+        return
+
+    print '[%s[%d commits]]' % (path, len(commit_list)),
+
+    ## add the commits into the database
+    for commit in commit_list:
+        db.AddCommit(commit)
+        sys.stdout.write('.')
+        sys.stdout.flush()
+    print
+
+
+def RecurseRebuild(db, repository, directory):
+    for path in os.listdir(directory):
+        path = os.path.join(directory, path)
+
+        if os.path.islink(path):
+            continue
+        
+        if os.path.isdir(path):
+            RecurseRebuild(db, repository, path)
+            continue
+        
+        if os.path.isfile(path):
+            if path[-2:] == ',v':
+                RebuildFile(db, repository, path)
+        
+
+def CommandRebuild():
+    ## connect to the database we are updating
+    db = cvsdbapi.ConnectDatabase()
+    repository = sys.argv[2]
+    RecurseRebuild(db, repository, repository)
+
+
+def usage():
+    print 'Usage: %s <command> [arguments]' % (sys.argv[0])
+    print 'Preforms administrative functions for the CVSdb database'
+    print 'Commands:'
+    print '  rebuild <repository>            rebuilds the CVSdb database'
+    print '                                  for all files in the repository'
+    print '  update <repository>             updates the CVSdb database for'
+    print '                                  all unrecorded commits'
+    print
+    sys.exit(1)
+
+
+## main
+if __name__ == '__main__':
+    ## check that a command was given
+    if len(sys.argv) < 2:
+        usage()
+
+    ## set the handler function for the command
+    command = sys.argv[1]
+    if string.lower(command) == 'rebuild':
+        commandFunction = CommandRebuild
+    elif string.lower(command) == 'update':
+        commandFunction = CommandUpdate
+    else:
+        print 'ERROR: unknown command %s' % (command)
+        usage()
+
+    ## run command
+    try:
+        commandFunction()
+    except KeyboardInterrupt:
+        print
+        print '** break **'
+        
+    sys.exit(0)

tools/loginfo-handler

@@ -0,0 +1,190 @@
+#!/usr/bin/python
+# -*- Mode: python -*-
+#
+# updates SQL database with new commit records
+#
+# -----------------------------------------------------------------------
+# Copyright (C) 2000 Jay Painter. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth below:
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
+#
+# -----------------------------------------------------------------------
+#
+# For tracking purposes, this software is identified by:
+#   $Id$
+#
+# -----------------------------------------------------------------------
+
+## BOOTSTRAP
+import sys, os, string
+_viewcvs_root = string.strip(open("/etc/viewcvs/root", "r").read())
+sys.path.append(os.path.join(_viewcvs_root, "lib"))
+##
+
+import getopt, re, cvsdbapi
+
+DEBUG_FLAG = 0
+
+## pre-compiled regular expressions
+_re_fileversion = re.compile("([^,]+)\,([^,]+)\,([^,]+)")
+
+
+## output functions
+def debug(text):
+    if DEBUG_FLAG:
+        print 'DEBUG(loginfo): %s' % (text)
+
+def warning(text):
+    print 'WARNING(loginfo): %s' % (text)
+
+def error(text):
+    print 'ERROR(loginfo): %s' % (text)
+    sys.exit(1)
+
+
+class FileData:
+
+    CHANGED = 1
+    ADDED   = 2
+    REMOVED = 3
+    
+    def __init__(self, file, directory, old_version, new_version):
+        self.file = file
+        self.directory = directory
+        self.old_version = old_version
+        self.new_version = new_version
+
+        ## set the state of this file from the
+        ## old_version and new_version information
+        if self.old_version == 'NONE':
+            self.type = self.ADDED
+        elif self.new_version == 'NONE':
+            self.type = self.REMOVED
+        else:
+            self.type = self.CHANGED
+
+
+def CommitFromFileData(repository, file_data):
+    ## consturct the full path for the RCS file
+    filename = os.path.join(repository, file_data.directory, file_data.file)
+
+    ## get the 'rlog' output for just this revision, and then convert
+    ## to a commit object
+    rlog_data = cvsdbapi.GetRLogData(filename, file_data.new_version)
+    commit_list = cvsdbapi.RLogDataToCommitList(repository, rlog_data)
+    commit = commit_list[0]
+
+    ## set the type of commit from the file_data setting
+    if file_data.type == file_data.CHANGED:
+        commit.SetTypeChange()
+    elif file_data.type == file_data.ADDED:
+        commit.SetTypeAdd()
+    elif file_data.type == file_data.REMOVED:
+        commit.SetTypeRemove()
+        
+    return commit
+
+
+def GetUnrecordedCommitList(repository, file_data):
+    filename = os.path.join(repository, file_data.directory, file_data.file)
+    return cvsdbapi.GetUnrecordedCommitList(repository, filename)
+
+
+def ProcessLoginfo(repository, stdin_list):
+    ## the first line in stdin is a space-separated list; the first
+    ## item in the list is the directory path being updated this run;
+    ## the rest of the items are the files being updated
+    list = string.split(stdin_list[0])
+
+    ## clean up the directory the following way: we don't want it
+    ## to begin with a path seperator, and we don't want it to end
+    ## with a path seperator
+    directory = list[0]
+    while directory[0] == os.sep:
+        directory = directory[1:]
+    while directory[-1] == os.sep:
+        directory = directory[:-1]
+
+    ## NOTE: SPECIAL HANDLING FOR NEW DIRECTORIES
+    ##       new directories have the first line form
+    ##       path/of/dir - New directory
+    if len(list) == 4:
+        if list[1] == '-' and list[2] == 'New' and list[3] == 'directory':
+            debug('new directory')
+            exit(0, file_hash, 1)
+
+    ## each file in the file list _should_ be of the form:
+    ## file-name,<old-ver>,<new-ver>
+    ## a new file has the keyword 'NONE' for old-ver
+    file_data_list = []
+    for item in list[1:]:
+        temp = _re_fileversion.match(item)
+        if not temp:
+            debug('failed match %s' % (item))
+            continue
+
+        filename = temp.group(1)
+        old_version = temp.group(2)
+        new_version = temp.group(3)
+        file_data =  FileData(filename, directory, old_version, new_version)
+        file_data_list.append(file_data)
+
+    ## convert FileData objects into Commit objects so we can insert them
+    ## into the database
+    commit_list = []
+    for file_data in file_data_list:
+        ## XXX: this is nasty: in the case of a removed file, we are not
+        ##      given enough information to find it in the rlog output!
+        ##      So instead, we rlog everything in the removed file, and
+        ##      add any commits not already in the database
+        if file_data.type == file_data.REMOVED:
+            temp = GetUnrecordedCommitList(repository, file_data)
+            commit_list = commit_list + temp
+        else:
+            commit_list.append(CommitFromFileData(repository, file_data))
+
+    ## add to the database
+    db = cvsdbapi.ConnectDatabase()
+    db.AddCommitList(commit_list)
+
+
+## MAIN
+if __name__ == '__main__':
+    ## get the repository from the environment
+    try:
+        repository = os.environ['CVSROOT']
+    except KeyError:
+        error('CVSROOT not in environment')
+
+    ## clean up the repository string: remove any trailing path seperater
+    while repository[-1] == os.sep:
+        repository = repository[:-1]
+
+    ## read all the lines from stdin
+    stdin_list = []
+    for line in sys.stdin.readlines():
+        stdin_list.append(string.rstrip(line))
+
+    ProcessLoginfo(repository, stdin_list)
+    sys.exit(0)

website/index.html

@@ -13,7 +13,8 @@
       (by <a href="mailto:zeller@think.de">Henner Zeller</a>).
       I wanted to make some changes and updates, but cvsweb was
       implemented in Perl (and rather poorly, IMO). So I undertook the 
-      task to convert the software to Python.
+      task to convert the software to
+      <a href="http://www.python.org/"><i>Python</i></a>.
     </p>
     <p>
       ViewCVS can browse directories, change logs, and specific
@@ -21,11 +22,11 @@
       show selections of files based on tags or branches.
     </p>
     <p>
-      ViewCVS is currently at version 0.2. It is almost a straight
+      ViewCVS is currently at version 0.4. It was a
       port of the cvsweb script, but has had numerous cleanups and other
       modifications, based on some of Python's strengths. There is
       still some "badness" in there, but I've been working on flushing 
-      that out, along with my work to start adding features. The
+      that out, along with a few new features. The
       functionality of ViewCVS is equal to that of cvsweb, minus the
       "annotation" support. Annotation requires read/write access to
       the CVS repository (at this time), and I believe that is a 
@@ -36,7 +37,7 @@
       The software is available for download:
     </p>
     <blockquote>
-      <a href="viewcvs-0.2.tar.gz">Version 0.2 of ViewCVS</a>
+      <a href="viewcvs-0.4.tar.gz">Version 0.4 of ViewCVS</a>
     </blockquote>
     <p>
       Of course, it is also available through ViewCVS itself:
@@ -46,14 +47,9 @@
     </blockquote>
 
     <p>
-      ViewCVS <font color=red>requires <strong>Python
-	1.5.2</strong></font>.
-    </p>
-
-    <p>
-      If you have any comments, questions, or suggestions, then please 
-      email me at
-      <a href="mailto:gstein@lyra.org">gstein@lyra.org</a>. 
+      ViewCVS requires <strong>Python 1.5</strong> (which has been out 
+      for a couple years and is readily available for your favorite
+      operating system).
     </p>
 
     <p>
@@ -62,36 +58,79 @@
     </p>
 
     <hr width="75&#37;">
-    <h2>FAQ</h2>
+    <h2>Mailing List</h2>
 
-    <dl>
-      <!-- one of (dd dt) -->
-      <dt><strong>I got an <code>AttributeError: urlencode</code></strong></dt>
-      <dd>
-	If you see the following traceback in your browser:
-	<blockquote>
-	  <pre>
-Traceback (innermost last):
-  File "/home/httpd/cgi-bin/viewcvs.cgi", line 2205, in ?
-    main()
-  File "/home/httpd/cgi-bin/viewcvs.cgi", line 2123, in main
-    query_string = sticky_query(query_dict)
-  File "/home/httpd/cgi-bin/viewcvs.cgi", line 444, in sticky_query
-    bare_query = urllib.urlencode(sticky_dict)
-AttributeError: urlencode
-</pre>
-	</blockquote>
-	This is indicative of using an earlier version of
-	Python. <code>urllib.urlencode()</code> was introduced in
-	Python 1.5.2.
-      </dd>
-    </dl>
+    <p>
+      If you have any comments, questions, suggestions, or patches,
+      then please send them to the
+      <a href="http://mailman.lyra.org/mailman/listinfo/viewcvs">ViewCVS
+	mailing list</a>.
+    </p>
+
+    <hr width="75&#37;">
+    <h2>Additional features over cvsweb</h2>
+
+    <ul>
+      <li>Colorization for Python files</li>
+      <li>Better reporting for unreadable files</li>
+      <li>More robust when given varying <code>rcsdiff</code> or
+	<code>rlog</code> outputs</li>
+      <li>Hard breaks in human-readable diffs</li>
+      <li>
+	The configuration file is optional (you can change the values
+	right in the CGI script and avoid the config file, if you so
+	choose). The config file syntax is also cleaner, since it is
+	human-manageable rather than source code.
+      </li>
+      <li>
+	Directories with a large number of files can be viewed.
+      </li>
+    </ul>
+
+    <p>
+      Future features, coming soon:
+    </p>
+    <ul>
+      <li>UI streamlining/simplification</li>
+      <li>Integration with CVS checkin auto-mail scripts</li>
+      <li>
+	<i>Suggestions? Send mail to the
+	  <a href="mailto:viewcvs@lyra.org">viewcvs@lyra.org</a>
+	  mailing list.
+	</i>
+      </li>
+    </ul>
+
+    <p>
+      Longer term:
+    </p>
+    <ul>
+      <li>Annotation ("blame") support (similar to cvsweb)</li>
+      <li>Integration with an indexer such as LXR</li>
+      <li>Additional colorizers</li>
+    </ul>
+
+    <hr width="75&#37;">
+    <h2>Colorization of Python files</h2>
+
+    <p>
+      Christophe Pelte suggested this feature: colorize Python source
+      files using
+      <a href="http://starship.python.net/crew/lemburg/SoftwareDescriptions.html#py2html.py"><i>py2html</i></a>
+      (by Marc-Andrew Lemburg, based on
+      <a href="http://starship.python.net/crew/just/code/PyFontify.py"><i>PyFontify</i></a>
+      by Just van Rossum). I've added this feature to ViewCVS 0.3,
+      along with a generalized plugin mechanism for custom coloring other
+      types of files. See the instructions within the viewcvs.cgi for
+      setting the <code>py2html_path</code> configuration variable if
+      you want to use this feature.
+    </p>
 
     <hr>
     <address><a href="mailto:gstein@lyra.org">Greg Stein</a></address>
 <!-- Created: Fri Dec  3 02:51:37 PST 1999 -->
 <!-- hhmts start -->
-Last modified: Wed Jan 12 03:12:22 PST 2000
+Last modified: Fri Mar 24 03:12:34 PST 2000
 <!-- hhmts end -->
   </body>
 </html>