Tag rename: V0_5 -> 0.5.0

git-svn-id: http://viewvc.tigris.org/svn/viewvc/tags/0.5.0@1317 8cb11bc2-c004-0410-86c3-e597b4017df7

INSTALL

@@ -9,20 +9,32 @@ INSTALLING VIEWCVS
    You need to have RCS installed. Specifically, "rlog", "rcsdiff",
    and "co". This script was tested against RedHat's rcs-5.7-10.rpm
 
-   Note, that the viewcvs.cgi-script needs to have READ-ONLY, physical
-   access to the repository (or a copy of it).  Therefore, rsh/ssh or
+   Note, that the viewcvs.cgi script needs to have READ-ONLY, physical
+   access to the CVS 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.
+   For the checkin database to work, you will need MySQL >= 3.22, 
+   and the Python DBAPI 2.0 module, MySQLdb.  This was tested with
+   MySQLdb 1.12.
 
-   If Python is not located in /usr/local/bin, then you'll need to
-   edit the first line of viewcvs.cgi.
+2) Installation is handled by the ./viewcvs-install script.  Run this
+   script and you will be prompted for a installation root path.
+   The default is /usr/local/viewcvs.  The installer sets the install 
+   path in some of the files, and ViewCVS cannot be moved to a 
+   different path after the install.
 
-3) Copy viewcvs.conf.dist to the same directory and RENAME it to
-   viewcvs.conf
+   Note: while 'root' is usually required to create /usr/local/viewcvs,
+   ViewCVS does not have to be installed as root, nor does it run as root.
+   It is just as valid to place ViewCVS in a home directory, too.
 
-4) Edit viewcvs.conf for your specific configuration. In particular,
-   examine the following configuration options:
+   Note: viewcvs-install will create directories if needed. It will
+   prompt before overwriting files that may have been modified (such
+   as viewcvs.conf), thus making it safe to install over the top of
+   a previous installation. It will always overwrite program files,
+   however.
+
+3) Edit <install-root>viewcvs.conf for your specific configuration. 
+   In particular, examine the following configuration options:
 
       cvs_roots
       default_root
@@ -32,11 +44,96 @@ INSTALLING VIEWCVS
    There are some other options that are usually nice to change. See
    viewcvs.conf for more information.
 
-5) That's it. Try it out.
+4) The CGI programs are in <install-root>/cgi/.  You can symlink to this
+   directory from somewhere in your published HTTP server path if your 
+   webserver is configured to follow symbolic links.  You can also copy
+   the installed <install-root>/cgi/*.cgi scripts after the install
+   (unlike the other files in ViewCVS, the CGI scripts can be moved).
 
-   Warning: ViewCVS has not been tested on web servers operating on the
-            Win32 platform.
+   NOTE: for security reasons, it is not advisable to install ViewCVS
+   directly into your published HTTP directory tree (due to the MySQL
+   passwords in viewcvs.conf).
 
+5) That's it for repository browsing.  Instructions for getting the
+   SQL checkin database working are below.
+
+
+WARNING: ViewCVS has not been tested on web servers operating on the
+         Win32 platform.
+
+
+
+SQL Checkin Database
+--------------------
+
+This feature is a clone of the Mozilla Project's Bonsai database.  It
+catalogs every commit in the CVS repository into a SQL database.  In fact,
+the databases are 100% compatible.
+
+Various queries can be preformed on the database.  After installing ViewCVS,
+there are some additional steps required to get the database working.
+
+1) You need MySQL >= 3.22, and the Python module MySQLdb >= 1.12 installed.
+
+2) You need to create a MySQL user who has permission to create databases.
+   Optionally, you can create a second user with read-only access to the
+   database.
+
+3) Run the <install-root>/make-database script.  It will prompt you for
+   your MySQL user, password, and the name of database you want to 
+   create.  The database name defaults to "ViewCVS".  This script creates
+   the database and sets up the empty tables.  If you run this on a 
+   existing ViewCVS database, you will loose all your data!
+
+4) Edit your <install-root>/viewcvs.conf file.  There is a [cvsdb]
+   section.  You will need to set:
+     
+      
+      host =             # MySQL database server host
+      database_name =    # the name of the database you created with
+                         # make-database
+      user =             # the read/write database user
+      passwd =           # password for read/write database user
+      readonly_user =    # the readonly database user -- it's pretty 
+                         # safe to use the read/write user here
+      readonly_passwd =  # password for the readonly user
+
+5) Two programs are provided for updating the checkin database, 
+   cvsdbadmin and loginfo-handler.  They serve two different purposes.
+   The cvsdbadmin program walks through your CVS repository and adds
+   every commit in every file.  This is commonly used for initalizing
+   the database from a repository which has been in use.  The 
+   loginfo-handler script is executed by the CVS server's CVSROOT/loginfo 
+   system upon each commit.  It makes real-time updates to the checkin
+   database as commits are made to the repository.
+
+   To build a database of all the commits in the CVS repository /home/cvs,
+   invoke: "./cvsdbadmin rebuild /home/cvs".  If you want to update
+   the checkin database, invoke: "./cvsdbadmin update /home/cvs".  The
+   update mode checks to see if a commit is already in the database,
+   and only adds it if it is abscent.
+
+   To get real-time updates, you'll want to checkout the CVSROOT module
+   from your CVS repository and edit CVSROOT/loginfo.  Add the line:
+
+       ALL (echo %{sVv}; cat) | <install-root>/loginfo-handler
+
+   If you have other scripts invoked by CVSROOT/loginfo, you will want
+   to make sure to change any running under the "DEFAULT" keyword to
+   "ALL" like the loginfo handler, and probably carefully read the
+   execution rules for CVSROOT/loginfo from the CVS manual.
+
+6) You may want to modify the HTML template files:
+
+      <install-root>/html-templates/queryformtemplate.html
+      <install-root>/html-templates/querytemplate.html
+
+   They're used by the queryform.cgi and query.cgi scripts generate
+   HTML output.  At some point, viewcvs.cgi, query.cgi, and queryform.cgi
+   will use the same mechanism for HTML generation, but not yet.
+
+7) You should be ready to go.  Load up the queryform.cgi script and give 
+   it a try.
 
 
 IF YOU HAVE PROBLEMS ...
@@ -75,7 +172,7 @@ If you've trouble to make viewcvs.cgi work:
 
  o check the ViewCVS home page:
 
-     http://www.lyra.org/greg/python/viewcvs/
+     http://www.lyra.org/viewcvs/
 
  o review the ViewCVS mailing list archive to see if somebody else had
    the same problem, and it was solved:

TODO

@@ -14,6 +14,19 @@ TODO ITEMS
 *) 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
 ----------
@@ -25,3 +38,5 @@ KNOWN BUGS
 
 *) 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 +1,199 @@
+#!/usr/bin/python
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+# CGI script to process and display queries to CVSdb
+#
+# This script is part of the ViewCVS package. More information can be
+# found at http://www.lyra.org/viewcvs/.
+#
+# -----------------------------------------------------------------------
+#
+
+#########################################################################
+#
+# INSTALL-TIME CONFIGURATION
+#
+# These values will be set during the installation process. During
+# development, they will remain None.
+#
+
+LIBRARY_DIR = None
+CONF_PATHNAME = None
+HTML_TEMPLATE_DIR = None
+
+# Adjust sys.path to include our library directory
+import sys
+
+if LIBRARY_DIR:
+  sys.path.insert(0, LIBRARY_DIR)
+else:
+  sys.path[:0] = ['../lib']	# any other places to look?
+
+#########################################################################
+
+import os, string, 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(HTML_TEMPLATE_DIR, "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 +1,54 @@
+#!/usr/bin/python
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+
+#########################################################################
+#
+# INSTALL-TIME CONFIGURATION
+#
+# These values will be set during the installation process. During
+# development, they will remain None.
+#
+
+LIBRARY_DIR = None
+CONF_PATHNAME = None
+HTML_TEMPLATE_DIR = None
+
+# Adjust sys.path to include our library directory
+import sys
+
+if LIBRARY_DIR:
+  sys.path.insert(0, LIBRARY_DIR)
+else:
+  sys.path[:0] = ['../lib']	# any other places to look?
+
+#########################################################################
+
+import os, string
+
+
+def HTMLHeader():
+    print "Content-type: text/html"
+    print
+    
+
+def Main():
+    HTMLHeader()
+    template_path = os.path.join(HTML_TEMPLATE_DIR, "queryformtemplate.html")
+    print open(template_path, "r").read()
+
+
+if __name__ == '__main__':
+    Main()

cgi/viewcvs.cgi

@@ -1,40 +1,19 @@
 #!/usr/local/bin/python
 # -*-python-*-
 #
-# viewcvs: View CVS repositories via a web browser
+# Copyright (C) 1999-2000 The ViewCVS Group. All Rights Reserved.
 #
-# Copyright (C) 1999-2000 Greg Stein. All Rights Reserved.
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
 #
-# 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.
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
 #
 # -----------------------------------------------------------------------
 #
-# This module is maintained by Greg and is available at:
-#    http://www.lyra.org/greg/python/viewcvs/
-#
-# For tracking purposes, this software is identified by:
-#   $Id$
+# viewcvs: View CVS repositories via a web browser
 #
 # -----------------------------------------------------------------------
 #
@@ -47,205 +26,19 @@
 # -----------------------------------------------------------------------
 #
 
-__version__ = '0.4'
+__version__ = '0.5'
 
 #########################################################################
 #
-# CONFIGURATION
+# INSTALL-TIME 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.
+# These values will be set during the installation process. During
+# development, they will remain None.
 #
 
-class Config:
-  _sections = ('general', 'images', 'options', 'colors', 'text')
-  _force_multi_value = ('cvs_roots', 'forbidden')
+LIBRARY_DIR = None
+CONF_PATHNAME = None
 
-  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 (section != 'text' and ',' in value) or \
-           opt in self._force_multi_value:
-          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)
-
-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
-
-cfg = Config()
-
-cfg.general.cvs_roots = {
-  # user-visible-name : path
-  "Development" : "/home/cvsroot",
-  }
-cfg.general.default_root = "Development"
-cfg.general.rcs_path = ''
-cfg.general.mime_types_file = ''
-cfg.general.address = '<a href="mailto:gstein@lyra.org">gstein@lyra.org</a>'
-cfg.general.main_title = 'CVS Repository'
-cfg.general.forbidden = ()
-
-cfg.images.logo = "/icons/apache_pb.gif", 259, 32
-cfg.images.back_icon = "/icons/small/back.gif", 16, 16
-cfg.images.dir_icon = "/icons/small/dir.gif",  16, 16
-cfg.images.file_icon = "/icons/small/text.gif", 16, 16
-
-cfg.colors.markup_log = "#ffffff"
-
-cfg.colors.diff_heading = "#99cccc"
-cfg.colors.diff_empty = "#cccccc"
-cfg.colors.diff_remove = "#ff9999"
-cfg.colors.diff_change = "#99ff99"
-cfg.colors.diff_add = "#ccccff"
-cfg.colors.diff_dark_change = "#99cc99"
-
-cfg.colors.even_odd = ("#ccccee", "#ffffff")
-
-cfg.colors.nav_header = "#9999ee"
-
-cfg.colors.text = "#000000"
-cfg.colors.background = "#ffffff"
-cfg.colors.alt_background = "#eeeeee"
-
-cfg.colors.column_header_normal = "#cccccc"
-cfg.colors.column_header_sorted = "#88ff88"
-
-cfg.colors.table_border = None	# no border
-
-cfg.options.sort_by = 'file'
-cfg.options.hide_attic = 1
-cfg.options.log_sort = 'date'
-cfg.options.diff_format = 'h'
-cfg.options.hide_cvsroot = 1
-cfg.options.hide_non_readable = 1
-cfg.options.show_author = 1
-cfg.options.hr_breakable = 1
-cfg.options.hr_funout = 1
-cfg.options.hr_ignore_white = 1
-cfg.options.hr_ignore_keyword_subst = 1
-cfg.options.allow_annotate = 0	### doesn't work yet!
-cfg.options.allow_markup = 1
-cfg.options.allow_compress = 1
-cfg.options.use_java_script = 1
-cfg.options.open_extern_window = 1
-cfg.options.extern_window_width = 600
-cfg.options.extern_window_height = 440
-cfg.options.checkout_magic = 1
-cfg.options.show_subdir_lastmod = 0
-cfg.options.show_logs = 1
-cfg.options.show_log_in_markup = 1
-cfg.options.allow_version_select = 1
-cfg.options.py2html_path = '.'
-cfg.options.short_log_len = 80
-cfg.options.table_padding = 2
-cfg.options.diff_font_face = 'Helvetica,Arial'
-cfg.options.diff_font_size = -1
-cfg.options.input_text_size = 12
-
-cfg.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/greg/python/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/greg/python/viewcvs/">ViewCVS distribution
-site</a>.
-Please send any suggestions, comments, etc. to
-<a href="mailto:gstein@lyra.org">Greg Stein</a>.
-</p>
-"""
-# ' stupid emacs...
-
-cfg.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.
-cfg.text.repository_info = """
-<!-- insert repository access instructions here -->
-"""
-
-cfg.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>
-"""
-
-#
-# CONFIGURATION END
-#
 #########################################################################
 
 import sys
@@ -257,8 +50,24 @@ import mimetypes
 import time
 import re
 import stat
-import ConfigParser
 
+#########################################################################
+#
+# Adjust sys.path to include our library directory
+#
+
+if LIBRARY_DIR:
+  sys.path.insert(0, LIBRARY_DIR)
+else:
+  sys.path[:0] = ['../lib']	# any other places to look?
+
+# time for our imports now
+import compat
+import config
+import popen
+
+
+#########################################################################
 
 checkout_magic_path = '~checkout~/'
 viewcvs_mime_type = 'text/vnd.viewcvs-markup'
@@ -284,11 +93,18 @@ _EOF_ERROR = 'error message found'	# rlog issued an error
 _FILE_HAD_ERROR = 'could not read file'
 
 header_comment = '''\
-<!-- ViewCVS       -- http://www.lyra.org/greg/python/viewcvs/
+<!-- ViewCVS       -- http://www.lyra.org/viewcvs/
      by Greg Stein -- mailto:gstein@lyra.org
   -->
 '''
 
+# for reading/writing between a couple descriptors
+CHUNK_SIZE = 8192
+
+# if your rlog doesn't use 77 '=' characters, then this must change
+LOG_END_MARKER = '=' * 77 + '\n'
+ENTRY_END_MARKER = '-' * 28 + '\n'
+
 
 class Request:
   def __init__(self):
@@ -393,34 +209,6 @@ class LogEntry:
     self.log = log
 
 
-#
-# Compatibility stuff for pre-1.5.2 versions of Python
-#
-# Two items: urllib.urlencode and time.strptime
-#
-try:
-  my_urlencode = urllib.urlencode
-except AttributeError:
-  def my_urlencode(dict):
-    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, '&')
-
-if hasattr(time, 'strptime'):
-  def my_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 my_strptime(timestr):
-    matches = _re_rev_date.match(timestr).groups()
-    return tuple(map(int, matches)) + (0, 1, -1)
-
-
 def redirect(location):
   print 'Status: 301 Moved'
   print 'Location:', location
@@ -462,7 +250,7 @@ def html_header(title):
 def html_footer():
   print '<hr noshade><table width="100&#37;" border=0 cellpadding=0 cellspacing=0><tr>'
   print '<td align=left><address>%s</address></td>' % cfg.general.address
-  print '<td align=right><a href="http://www.lyra.org/greg/python/viewcvs/">ViewCVS %s</a><br>' % __version__
+  print '<td align=right><a href="http://www.lyra.org/viewcvs/">ViewCVS %s</a><br>' % __version__
   print 'by <a href="mailto:gstein@lyra.org">Greg Stein</a>'
   print '</td></tr></table>'
   print '</body></html>'
@@ -473,7 +261,7 @@ def sticky_query(dict):
     value = dict.get(varname)
     if value is not None and value != default_settings.get(varname, ''):
       sticky_dict[varname] = value
-  return my_urlencode(sticky_dict)
+  return compat.urlencode(sticky_dict)
 
 def toggle_query(query_dict, which, value=None):
   dict = query_dict.copy()
@@ -571,7 +359,7 @@ def download_link(request, url, revision, text, mime_type=None):
     print ' target="cvs_checkout"'
     if cfg.options.use_java_script:
       print " onClick=\"window.open('%s','cvs_checkout'," \
-            "'resizeable,scrollbars" % full_url,
+            "'resizeable=1,scrollbars=1" % full_url,
       if mime_type == 'text/html':
         print ',status,toolbar',
       print "');\""
@@ -667,7 +455,7 @@ def markup_stream_default(fp):
   while 1:
     ### technically, the htmlify() could fail if something falls across
     ### the chunk boundary. TFB.
-    chunk = fp.read(8192)
+    chunk = fp.read(CHUNK_SIZE)
     if not chunk:
       break
     sys.stdout.write(htmlify(chunk))
@@ -694,8 +482,83 @@ def markup_stream_python(fp):
     html = re.sub(_re_rewrite_email, r'<a href="mailto:\1">\1</a>', html)
     sys.stdout.write(html)
 
+def markup_stream_enscript(lang, fp):
+  sys.stdout.flush()
+  cmd = "%senscript --color -W html -E%s -o - - 2> /dev/null " \
+        "| sed -n '/^<PRE>$/,/<\\/PRE>$/p'" % \
+        (cfg.options.enscript_path, lang,)
+  enscript = os.popen(cmd, "w")
+  while 1:
+    chunk = fp.read(CHUNK_SIZE)
+    if not chunk:
+      break
+    enscript.write(chunk)
+  enscript.close()
+
 markup_streamers = {
-  '.py' : markup_stream_python,
+#  '.py' : markup_stream_python,
+  }
+
+### this sucks... we have to duplicate the extensions defined by enscript
+enscript_extensions = {
+  '.c' : 'c',
+  '.h' : 'c',
+  '.c++' : 'cpp',
+  '.C' : 'cpp',
+  '.H' : 'cpp',
+  '.cpp' : 'cpp',
+  '.cc' : 'cpp',
+  '.cxx' : 'cpp',
+  '.m' : 'objc',
+  '.scm' : 'scheme',
+  '.scheme' : 'scheme',
+  '.el' : 'elisp',
+  '.ada' : 'ada',
+  '.adb' : 'ada',
+  '.ads' : 'ada',
+  '.s' : 'asm',
+  '.S' : 'asm',
+  '.st' : 'states',
+  '.tcl' : 'tcl',
+  '.v' : 'verilog',
+  '.vh' : 'verilog',
+  '.htm' : 'html',
+  '.html' : 'html',
+  '.shtml' : 'html',
+  '.vhd' : 'vhdl',
+  '.vhdl' : 'vhdl',
+  '.scr' : 'synopsys',
+  '.syn' : 'synopsys',
+  '.synth' : 'synopsys',
+  '.idl' : 'idl',
+  '.hs' : 'haskell',
+  '.lhs' : 'haskell',
+  '.gs' : 'haskell',
+  '.lgs' : 'haskell',
+  '.pm' : 'perl',
+  '.pl' : 'perl',
+  '.eps' : 'postscript',
+  '.EPS' : 'postscript',
+  '.ps' : 'postscript',
+  '.PS' : 'postscript',
+  '.js' : 'javascript',
+  '.java' : 'java',
+  '.pas' : 'pascal',
+  '.pp' : 'pascal',
+  '.p' : 'pascal',
+  '.f' : 'fortran',
+  '.F' : 'fortran',
+  '.awk' : 'awk',
+  '.sh' : 'sh',
+  '.vba' : 'vba',
+
+  ### use enscript or py2html?
+  '.py' : 'python',
+  }
+enscript_filenames = {
+  '.emacs' : 'elisp',
+  'Makefile' : 'makefile',
+  'makefile' : 'makefile',
   }
 
 def markup_stream(request, fp, revision, mime_type):
@@ -730,14 +593,26 @@ def markup_stream(request, fp, revision, mime_type):
       print 'Tag: <b>%s</b><br>' % tag
   print '</td></tr></table>'
 
-  url = download_url(request, file_url, revision, mime_type)
   print '<hr noshade>'
   if mime_type[:6] == 'image/':
+    url = download_url(request, file_url, revision, mime_type)
     print '<img src="%s%s"><br>' % (url, request.amp_query)
   else:
     basename, ext = os.path.splitext(filename)
-    streamer = markup_streamers.get(ext, markup_stream_default)
-    streamer(fp)
+    streamer = markup_streamers.get(ext)
+    if streamer:
+      streamer(fp)
+    elif not cfg.options.use_enscript:
+      markup_stream_default(fp)
+    else:
+      lang = enscript_extensions.get(ext)
+      if not lang:
+        lang = enscript_filenames.get(basename)
+      if lang and lang not in cfg.options.disable_enscript_lang:
+        markup_stream_enscript(lang, fp)
+      else:
+        markup_stream_default(fp)
+  html_footer()
 
 def get_file_data(full_name):
   """Return a sequence of tuples containing various data about the files.
@@ -836,10 +711,10 @@ def parse_log_header(fp):
       elif line[:14] == 'symbolic names':
         # start parsing the tag information
         parsing_tags = 1
-      elif line == '----------------------------\n':
+      elif line == ENTRY_END_MARKER:
         # end of the headers
         break
-      elif line[:10] == '==========':
+      elif line == LOG_END_MARKER:
         # end of this file's log information
         eof = _EOF_FILE
         break
@@ -899,9 +774,9 @@ def parse_log_entry(fp):
       break
     if line[:9] == 'branches:':
       continue
-    if line == '----------------------------\n':
+    if line == ENTRY_END_MARKER:
       break
-    if line[:10] == '==========':
+    if line == LOG_END_MARKER:
       # end of this file's log information
       eof = _EOF_FILE
       break
@@ -912,7 +787,7 @@ def parse_log_entry(fp):
     # there was a parsing error
     return None, eof
 
-  date = int(time.mktime(my_strptime(match.group(1)))) - time.timezone
+  date = int(time.mktime(compat.cvs_strptime(match.group(1)))) - time.timezone
 
   return LogEntry(rev, date,
                   # author, state, lines changed
@@ -925,7 +800,7 @@ def skip_file(fp):
     line = fp.readline()
     if not line:
       break
-    if line[:10] == '==========':
+    if line == LOG_END_MARKER:
       break
 
 def process_rlog_output(rlog, full_name, view_tag, fileinfo, alltags):
@@ -1062,18 +937,18 @@ def get_logs(full_name, files, view_tag):
     chunk = files[:chunk_size]
     del files[:chunk_size]
 
-    arglist = string.join(chunk, "' '" + full_name + '/')
+    # prepend the full pathname for each file
+    for i in range(len(chunk)):
+      chunk[i] = full_name + '/' + chunk[i]
+
     if view_tag:
       # NOTE: can't pass tag on command line since a tag may contain "-"
       #       we'll search the output for the appropriate revision
-      rlog = os.popen("%srlog '%s/%s' 2>&1" %
-                      (cfg.general.rcs_path, full_name, arglist),
-                      "r")
+      rlog = popen.popen(cfg.general.rcs_path + 'rlog', chunk, 'r')
     else:
       # fetch the latest revision on the default branch
-      rlog = os.popen("%srlog -r '%s/%s' 2>&1" %
-                      (cfg.general.rcs_path, full_name, arglist),
-                      "r")
+      chunk = ('-r',) + tuple(chunk)
+      rlog = popen.popen(cfg.general.rcs_path + 'rlog', chunk, 'r')
 
     process_rlog_output(rlog, full_name, view_tag, fileinfo, alltags)
 
@@ -1086,6 +961,10 @@ def get_logs(full_name, files, view_tag):
     ###
     ### more work for later...
 
+    if rlog.close():
+      ### what to do?
+      pass
+
   return fileinfo, alltags.keys()
 
 def revcmp(rev1, rev2):
@@ -1277,7 +1156,7 @@ def view_directory(request):
     if isdir:
       if not hideattic and file == 'Attic':
         continue
-      if where == '' and (file == 'CVSROOT' or file in cfg.general.forbidden):
+      if where == '' and (file == 'CVSROOT' or cfg.is_forbidden(file)):
         continue
 
       print '<tr bgcolor="%s"><td>' % cfg.colors.even_odd[cur_row % 2]
@@ -1412,12 +1291,10 @@ def view_directory(request):
 
 def fetch_log(full_name, which_rev=None):
   if which_rev:
-    rev_flag = '-r' + which_rev
+    args = ('-r' + which_rev, full_name)
   else:
-    rev_flag = ''
-  rlog = os.popen("%srlog %s '%s' 2>&1" %
-                  (cfg.general.rcs_path, rev_flag, full_name),
-                  "r")
+    args = (full_name,)
+  rlog = popen.popen(cfg.general.rcs_path + 'rlog', args, 'r')
 
   header, eof = parse_log_header(rlog)
   filename = header.filename
@@ -1905,18 +1782,14 @@ def view_checkout(request):
     ### validate it?
     pass
   else:
-    mime_type, encoding = mimetypes.guess_type(where)
-    if not mime_type:
-      mime_type = 'text/plain'
+    mime_type = request.mime_type
 
   if rev:
     rev_flag = '-p' + rev
   else:
     rev_flag = '-p'
 
-  fp = os.popen("%sco '%s' '%s' 2>&1" %
-                (cfg.general.rcs_path, rev_flag, full_name),
-                'r')
+  fp = popen.popen(cfg.general.rcs_path + 'co', (rev_flag, full_name), 'r')
 
   # header from co:
 
@@ -1945,7 +1818,8 @@ def view_checkout(request):
           (header, filename, where))
 
   if mime_type == viewcvs_mime_type:
-    markup_stream(request, fp, revision, mime_type)
+    # use the "real" MIME type
+    markup_stream(request, fp, revision, request.mime_type)
   else:
     http_header(mime_type)
     while 1:
@@ -1955,14 +1829,22 @@ def view_checkout(request):
       sys.stdout.write(chunk)
 
 def view_annotate(request):
-  ### dunno what this is for... check against cvsweb
-  some_value = request.query_dict['annotate']
+  rev = request.query_dict['annotate']
+
+  pathname, filename = os.path.split(request.where)
+  if pathname[-6:] == '/Attic':
+    pathname = pathname[:-6]
+
+  http_header()
+  navigate_header(request, request.url, pathname, filename, rev, 'view')
+  print '<hr noshade>'
+
+  import blame
+  blame.make_html(request.cvsroot, request.where + ',v', rev)
 
-  ### testing
-  html_header('annotate')
-  print "annotate"
   html_footer()
 
+
 _re_extract_rev = re.compile(r'^[-+]+ [^\t]+\t([^\t]+)\t((\d+\.)+\d+)$')
 _re_extract_info = re.compile(r'@@ \-([0-9]+).*\+([0-9]+).*@@(.*)')
 _re_extract_diff = re.compile(r'^([-+ ])(.*)')
@@ -2026,11 +1908,17 @@ def human_readable_diff(request, fp, rev1, rev2, sym1, sym2):
        (cfg.options.diff_font_face, cfg.options.diff_font_size)
   left_row = right_row = 0
 
+  # this will be set to true if any changes are found
+  changes_seen = 0
+
   while 1:
     line = fp.readline()
     if not line:
       break
 
+    # we've seen some kind of change
+    changes_seen = 1
+
     if line[:2] == '@@':
       match = _re_extract_info.match(line)
       print '<tr bgcolor="%s"><td width="50&#37;">' % cfg.colors.diff_heading
@@ -2046,6 +1934,11 @@ def human_readable_diff(request, fp, rev1, rev2, sym1, sym2):
       state = 'dump'
       left_col = [ ]
       right_col = [ ]
+    elif line[0] == '\\':
+      # \ No newline at end of file
+      flush_diff_rows(state, left_col, right_col)
+      left_col = [ ]
+      right_col = [ ]
     else:
       match = _re_extract_diff.match(line)
       line = spaced_html_text(match.group(2))
@@ -2072,10 +1965,11 @@ def human_readable_diff(request, fp, rev1, rev2, sym1, sym2):
         left_col = [ ]
         right_col = [ ]
 
-  flush_diff_rows(state, left_col, right_col)
-  if not state:
+  if changes_seen:
+    flush_diff_rows(state, left_col, right_col)
+  else:
     print '<tr><td colspan=2>&nbsp;</td></tr>'
-    print '<tr bgcolor="%s"><td colspan=2 align=center><b>- No viewable change -</b></td></tr>' % (cfg.colors.diff_empty)
+    print '<tr bgcolor="%s"><td colspan=2 align=center><br><b>- No changes -</b><br>&nbsp;</td></tr>' % (cfg.colors.diff_empty)
 
   print '</table><br><hr noshade width="100&#37;">'
   print '<table border=0 cellpadding=10><tr><td>'
@@ -2168,45 +2062,51 @@ def view_diff(request, cvs_filename):
       rev2 = r2[:idx]
       sym2 = r2[idx+1:]
 
-  ### check rev1, rev2 for well-formed-ness (security reasons)
-
   if revcmp(rev1, rev2) > 0:
     rev1, rev2 = rev2, rev1
     sym1, sym2 = sym2, sym1
 
   human_readable = 0
+  unified = 0
+
+  args = [ ]
+
   format = query_dict['diff_format']
   if format == 'c':
-    diff_type = '-c'
+    args.append('-c')
     diff_name = 'Context diff'
   elif format == 's':
-    diff_type = '--side-by-side --width=164'
+    args.append('--side-by-side')
+    args.append('--width=164')
     diff_name = 'Side by Side'
   elif format == 'H':
-    diff_type = '--unified=15'
+    args.append('--unified=15')
     diff_name = 'Long Human readable'
     human_readable = 1
+    unified = 1
   elif format == 'h':
-    diff_type = '-u'
+    args.append('-u')
     diff_name = 'Human readable'
     human_readable = 1
+    unified = 1
   elif format == 'u':
-    diff_type = '-u'
+    args.append('-u')
     diff_name = 'Unidiff'
+    unified = 1
   else:
     error('Diff format %s not understood' % format, '400 Bad arguments')
 
   if human_readable:
     if cfg.options.hr_funout:
-      diff_type = diff_type + ' -p'
+      args.append('-p')
     if cfg.options.hr_ignore_white:
-      diff_type = diff_type + ' -w'
+      args.append('-w')
     if cfg.options.hr_ignore_keyword_subst:
-      diff_type = diff_type + ' -kk'
+      args.append('-kk')
+
+  args[len(args):] = ['-r' + rev1, '-r' + rev2, cvs_filename]
+  fp = popen.popen(cfg.general.rcs_path + 'rcsdiff', args, 'r')
 
-  fp = os.popen("%srcsdiff %s '-r%s' '-r%s' '%s' 2>&1" %
-                (cfg.general.rcs_path, diff_type, rev1, rev2, cvs_filename),
-                'r')
   if human_readable:
     http_header()
     human_readable_diff(request, fp, rev1, rev2, sym1, sym2)
@@ -2214,7 +2114,7 @@ def view_diff(request, cvs_filename):
 
   http_header('text/plain')
 
-  if diff_type == '-u':
+  if unified:
     f1 = '--- ' + cvsroot
     f2 = '+++ ' + cvsroot
   else:
@@ -2238,9 +2138,13 @@ def view_diff(request, cvs_filename):
     print line[:-1]
 
 def handle_config():
+  global cfg
+  cfg = config.Config()
+  cfg.set_defaults()
+
   # load in configuration information from the config file
-  ### allow changes and paths here...??
-  cfg.load_config('viewcvs.conf')
+  pathname = CONF_PATHNAME or 'viewcvs.conf'
+  cfg.load_config(pathname, os.environ.get('HTTP_HOST'))
 
   global default_settings
   default_settings = {
@@ -2280,7 +2184,7 @@ def main():
     redirect(url + '/' + request.qmark_query)
 
   # check the forbidden list
-  if request.module in cfg.general.forbidden:
+  if cfg.is_forbidden(request.module):
     error('Access to "%s" is forbidden.' % request.module, '403 Forbidden')
 
   if isdir:

cgi/viewcvs.conf.dist

@@ -3,7 +3,7 @@
 # Configuration file for ViewCVS
 #
 # Information on ViewCVS is located at the following web site:
-#     http://www.lyra.org/greg/python/viewcvs/
+#     http://www.lyra.org/viewcvs/
 #
 #---------------------------------------------------------------------------
 
@@ -28,6 +28,8 @@
 #    long_intro
 #    repository_info
 #
+#    use_enscript
+#
 # For Python source colorization:
 #
 #    py2html_path
@@ -94,9 +96,55 @@ 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).
 #
+# This configuration can be a simple list of modules, or it can get quite
+# complex:
+#
+#   *) The "!" can be used before a module to explicitly state that it
+#      is NOT forbidden. Whenever this form is seen, then all modules will
+#      be forbidden unless one of the "!" modules match.
+#
+#   *) Shell-style "glob" expressions may be used. "*" will match any
+#      sequence of zero or more characters, "?" will match any single
+#      character, "[seq]" will match any character in seq, and "[!seq]"
+#      will match any character not in seq.
+#
+#   *) Tests are performed in sequence. The first match will terminate the
+#      testing. This allows for more complex allow/deny patterns.
+#
+# Tests are case-sensitive.
+#
 forbidden =
-# forbidden = example
-# forbidden = example1, example2
+
+# Some examples:
+#
+# Disallow "example" but allow all others:
+#   forbidden = example
+#
+# Disallow "example1" and "example2" but allow all others:
+#   forbidden = example1, example2
+#
+# Allow *only* "example1" and "example2":
+#   forbidden = !example1, !example2
+#
+# Forbid modules starting with "x":
+#   forbidden = x*
+#
+# Allow modules starting with "x" but no others:
+#   forbidden = !x*
+#
+# Allow "xml", forbid other modules starting with "x", and allow the rest:
+#   forbidden = !xml, x*, !*
+#
+
+#---------------------------------------------------------------------------
+[cvsdb]
+
+#host = localhost
+#database_name = ViewCVS
+#user = 
+#passwd = 
+#readonly_user = 
+#readonly_passwd = 
 
 #---------------------------------------------------------------------------
 [images]
@@ -192,7 +240,7 @@ long_intro =
     </p>
     <p>
     This script
-    (<a href="http://www.lyra.org/greg/python/viewcvs/">ViewCVS</a>)
+    (<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
@@ -204,7 +252,7 @@ long_intro =
     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/greg/python/viewcvs/">ViewCVS distribution
+    <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>.
@@ -297,7 +345,7 @@ hr_ignore_keyword_subst = 1
 # 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_annotate = 1
 
 # allow pretty-printed version of files
 allow_markup = 1
@@ -368,4 +416,53 @@ diff_font_size = -1
 # the width of the textinput in the request-diff-form
 input_text_size = 12
 
+# should we use 'enscript' for syntax coloring?
+use_enscript = 0
+
+#
+# if the enscript program is not on the path, set this value
+# Note: there should be a trailing slash
+#
+enscript_path =
+# enscript_path = /usr/bin/
+
+#
+# ViewCVS has its own set of mappings from filename extensions and filenames
+# to languages. If the language is not supported by enscript, then it can
+# be listed here to disable the use of enscript.
+#
+disable_enscript_lang =
+# disable_enscript_lang = perl, cpp
+
+#---------------------------------------------------------------------------
+[vhosts]
+### DOC
+
+# vhost1 = glob1, glob2
+# vhost2 = glob3, glob4
+
+# [vhost1-section]
+# option = value
+# [vhost1-othersection]
+# option = value
+# [vhost2-section]
+# option = value
+
+#
+# Here is an example:
+#
+# [vhosts]
+# lyra = *lyra.org
+#
+# [lyra-general]
+# forbidden = hideme
+#
+# [lyra-options]
+# show_logs = 0
+#
+# Note that "lyra" is the "canonical" name for all hosts in the lyra.org
+# domain. This canonical name is then used within the additional, vhost-
+# specific sections to override specific values in the common sections.
+#
+
 #---------------------------------------------------------------------------

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/blame.py

@@ -0,0 +1,733 @@
+#!/usr/local/bin/python
+# -*-python-*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+# Copyright (C) 2000 Curt Hagenlocher <curt@hagenlocher.org>
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+# blame.py: Annotate each line of a CVS file with its author,
+#           revision #, date, etc.
+#
+# -----------------------------------------------------------------------
+#
+# This software is being maintained as part of the ViewCVS project.
+# Information is available at:
+#    http://www.lyra.org/viewcvs/
+#
+# This file is based on the cvsblame.pl portion of the Bonsai CVS tool,
+# developed by Steve Lamm for Netscape Communications Corporation.  More
+# information about Bonsai can be found at
+#    http://www.mozilla.org/bonsai.html
+#
+# cvsblame.pl, in turn, was based on Scott Furman's cvsblame script
+#
+# -----------------------------------------------------------------------
+#
+
+import string
+import sys
+import os
+import re
+import time
+import math
+import cgi
+
+path_sep    = os.path.normpath('/')[-1]
+
+class CVSParser:
+  # Precompiled regular expressions
+  nonws_token = re.compile('^([^;@][^;\\s]*)\\s*')
+  semic_token = re.compile('^;\\s*')
+  rcsen_token = re.compile('^@([^@]*)')
+  undo_escape = re.compile('@@')
+  single_at   = re.compile('([^@]|^)@([^@]|$)')
+  rcs_tree    = re.compile('^\\d')
+  trunk_rev   = re.compile('^[0-9]+\\.[0-9]+$')
+  last_branch = re.compile('(.*)\\.[0-9]+')
+  is_branch   = re.compile('(.*)\\.0\\.([0-9]+)')
+  d_command   = re.compile('^d(\d+)\\s(\\d+)')
+  a_command   = re.compile('^a(\d+)\\s(\\d+)')
+
+  SECONDS_PER_DAY = 86400
+
+  def __init__(self):
+    self.Reset()
+
+  def Reset(self):
+    self.line_buffer = ''
+    self.rcsfile = None
+    self.debug = 0
+    self.last_revision = {}
+    self.prev_revision = {}
+    self.revision_date = {}
+    self.revision_author = {}
+    self.revision_branches = {}
+    self.next_delta = {}
+    self.prev_delta = {}
+    self.feof = 0
+    self.tag_revision = {}
+    self.revision_symbolic_name = {}
+    self.timestamp = {}
+    self.revision_ctime = {}
+    self.revision_age = {}
+    self.revision_log = {}
+    self.revision_deltatext = {}
+    self.revision_map = []
+    self.lines_added  = {}
+    self.lines_removed = {}
+
+  # Get the next token from the RCS file
+  def get_token(self):
+    # Erase all-whitespace lines
+    while len(self.line_buffer) == 0:
+      self.line_buffer = self.rcsfile.readline()
+      if self.line_buffer == '':
+        raise RuntimeError, 'EOF'
+      self.line_buffer = string.lstrip(self.line_buffer)
+
+    # A string of non-whitespace characters is a token
+    match = self.nonws_token.match(self.line_buffer)
+    if match:
+      self.line_buffer = self.nonws_token.sub('', self.line_buffer)
+      return match.group(1)
+
+    # ...and so is a single semicolon
+    if self.semic_token.match(self.line_buffer):
+      self.line_buffer = self.semic_token.sub('', self.line_buffer)
+      return ';'
+
+    # ...or an RCS-encoded string that starts with an @ character
+    match = self.rcsen_token.match(self.line_buffer)
+    self.line_buffer = self.rcsen_token.sub('', self.line_buffer)
+    token = match.group(1)
+
+    # Detect single @ character used to close RCS-encoded string
+    while string.find(self.line_buffer, '@') < 0 or not self.single_at.search(self.line_buffer):
+      token = token + self.line_buffer
+      self.line_buffer = self.rcsfile.readline()
+      if self.line_buffer == '':
+        raise RuntimeError, 'EOF'
+
+    # Retain the remainder of the line after the terminating @ character
+    i = string.rindex(self.line_buffer, '@')
+    token = token + self.line_buffer[:i]
+    self.line_buffer = self.line_buffer[i+1:]
+
+    # Undo escape-coding of @ characters.
+    token = self.undo_escape.sub('@', token)
+
+    # Digest any extra blank lines
+    while len(self.line_buffer) == 0 or self.line_buffer == '\n':
+      self.line_buffer = self.rcsfile.readline()
+      if self.line_buffer == '':
+        self.feof = 1
+        break
+
+    if token[-1:] == '\n':
+      token = token[:-1]
+
+    return token
+
+  # Try to match the next token from the input buffer
+  def match_token(self, match):
+    token = self.get_token()
+    if token != match:
+      raise RuntimeError, ('Unexpected parsing error in RCS file.\n' +
+                           'Expected token: %s, but saw: %s' % (match, token))
+
+  # Push RCS token back into the input buffer.
+  def unget_token(self, token):
+    self.line_buffer = token + " " + self.line_buffer
+
+  # Map a tag to a numerical revision number.  The tag can be a symbolic
+  # branch tag, a symbolic revision tag, or an ordinary numerical
+  # revision number.
+  def map_tag_to_revision(self, tag_or_revision):
+    try:
+      revision = self.tag_revision[tag_or_revision]
+      match = self.is_branch.match(revision)
+      if match:
+        branch = match.group(1) + '.' + match.group(2)
+        if self.last_revision.get(branch):
+          return self.last_revision[branch]
+        else:
+          return match.group(1)
+      else:
+        return revision
+    except:
+      return ''
+
+  # Construct an ordered list of ancestor revisions to the given
+  # revision, starting with the immediate ancestor and going back
+  # to the primordial revision (1.1).
+  #
+  # Note: The generated path does not traverse the tree the same way
+  #       that the individual revision deltas do.  In particular,
+  #       the path traverses the tree "backwards" on branches.
+  def ancestor_revisions(self, revision):
+    ancestors = []
+    revision = self.prev_revision.get(revision)
+    while revision:
+      ancestors.append(revision)
+      revision = self.prev_revision.get(revision)
+
+    return ancestors
+
+  # Extract the given revision from the digested RCS file.
+  # (Essentially the equivalent of cvs up -rXXX)
+  def extract_revision(self, revision):
+    path = []
+    add_lines_remaining = 0
+    start_line = 0
+    count = 0
+    while revision:
+      path.append(revision)
+      revision = self.prev_delta.get(revision)
+    path.reverse()
+    path = path[1:]  # Get rid of head revision
+
+    text = string.split(self.revision_deltatext[self.head_revision], '\n')
+
+    # Iterate, applying deltas to previous revision
+    for revision in path:
+      adjust = 0
+      diffs = string.split(self.revision_deltatext[revision], '\n')
+      self.lines_added[revision]   = 0
+      self.lines_removed[revision] = 0
+      lines_added_now = 0
+      lines_removed_now = 0
+
+      for command in diffs:
+        dmatch = self.d_command.match(command)
+        amatch = self.a_command.match(command)
+        if add_lines_remaining > 0:
+          # Insertion lines from a prior "a" command
+          text.insert(start_line + adjust, command)
+          add_lines_remaining = add_lines_remaining - 1
+          adjust = adjust + 1
+        elif dmatch:
+          # "d" - Delete command
+          start_line = string.atoi(dmatch.group(1))
+          count      = string.atoi(dmatch.group(2))
+          begin = start_line + adjust - 1
+          del text[begin:begin + count]
+          adjust = adjust - count
+          lines_removed_now = lines_removed_now + count
+        elif amatch:
+          # "a" - Add command
+          start_line = string.atoi(amatch.group(1))
+          count      = string.atoi(amatch.group(2))
+          add_lines_remaining = count
+          lines_added_now = lines_added_now + count
+        else:
+          raise RuntimeError, 'Error parsing diff commands'
+
+      self.lines_added[revision]   = self.lines_added[revision]   + lines_added_now
+      self.lines_removed[revision] = self.lines_removed[revision] + lines_removed_now
+    return text
+
+  def parse_rcs_admin(self):
+    while 1:
+      # Read initial token at beginning of line
+      token = self.get_token()
+
+      # We're done once we reach the description of the RCS tree
+      if self.rcs_tree.match(token):
+        self.unget_token(token)
+        return
+
+      # print "token:", token
+
+      if token == "head":
+        self.head_revision = self.get_token()
+        self.get_token()         # Eat semicolon
+      elif token == "branch":
+        self.principal_branch = self.get_token()
+        self.get_token()         # Eat semicolon
+      elif token == "symbols":
+        # Create an associate array that maps from tag name to
+        # revision number and vice-versa.
+        while 1:
+          tag = self.get_token()
+          if tag == ';':
+            break
+          (tag_name, tag_rev) = string.split(tag, ':')
+          self.tag_revision[tag_name] = tag_rev
+          self.revision_symbolic_name[tag_rev] = tag_name
+      elif token == "comment":
+        self.file_description = self.get_token()
+        self.get_token()         # Eat semicolon
+
+      # Ignore all these other fields - We don't care about them.         
+      elif token in ("locks", "strict", "expand", "access"):
+        while 1:
+          tag = self.get_token()
+          if tag == ';':
+            break
+      else:
+        pass
+        # warn("Unexpected RCS token: $token\n")
+
+    raise RuntimeError, "Unexpected EOF";
+
+  # Construct dicts that represent the topology of the RCS tree
+  # and other arrays that contain info about individual revisions.
+  #
+  # The following dicts are created, keyed by revision number:
+  #   self.revision_date     -- e.g. "96.02.23.00.21.52"
+  #   self.timestamp         -- seconds since 12:00 AM, Jan 1, 1970 GMT
+  #   self.revision_author   -- e.g. "tom"
+  #   self.revision_branches -- descendant branch revisions, separated by spaces,
+  #                             e.g. "1.21.4.1 1.21.2.6.1"
+  #   self.prev_revision     -- revision number of previous *ancestor* in RCS tree.
+  #                             Traversal of this array occurs in the direction
+  #                             of the primordial (1.1) revision.
+  #   self.prev_delta        -- revision number of previous revision which forms
+  #                             the basis for the edit commands in this revision.
+  #                             This causes the tree to be traversed towards the
+  #                             trunk when on a branch, and towards the latest trunk
+  #                             revision when on the trunk.
+  #   self.next_delta        -- revision number of next "delta".  Inverts prev_delta.
+  #
+  # Also creates self.last_revision, keyed by a branch revision number, which
+  # indicates the latest revision on a given branch,
+  #   e.g. self.last_revision{"1.2.8"} == 1.2.8.5
+
+  def parse_rcs_tree(self):
+    while 1:
+      revision = self.get_token()
+
+      # End of RCS tree description ?
+      if revision == 'desc':
+        self.unget_token(revision)
+        return
+
+      is_trunk_revision = self.trunk_rev.match(revision) is not None
+
+      self.tag_revision[revision] = revision
+      branch = self.last_branch.match(revision).group(1)
+      self.last_revision[branch] = revision
+
+      # Parse date
+      self.match_token('date')
+      date = self.get_token()
+      self.revision_date[revision] = date
+      self.match_token(';')
+
+      # Convert date into timestamp
+      date_fields = string.split(date, '.') + ['0', '0', '0']
+      date_fields = map(string.atoi, date_fields)
+      if date_fields[0] < 100:
+        date_fields[0] = date_fields[0] + 1900
+      self.timestamp[revision] = time.mktime(date_fields)
+
+      # Pretty print the date string
+      ltime = time.localtime(self.timestamp[revision])
+      formatted_date = time.strftime("%d %b %Y %H:%M", ltime)
+      self.revision_ctime[revision] = formatted_date
+
+      # Save age
+      self.revision_age[revision] = (
+              (time.time() - self.timestamp[revision]) / self.SECONDS_PER_DAY)
+
+      # Parse author
+      self.match_token('author')
+      author = self.get_token()
+      self.revision_author[revision] = author
+      self.match_token(';')
+
+      # Parse state
+      self.match_token('state')
+      while self.get_token() != ';':
+        pass
+
+      # Parse branches
+      self.match_token('branches')
+      branches = ''
+      while 1:
+        token = self.get_token()
+        if token == ';':
+          break
+        self.prev_revision[token] = revision
+        self.prev_delta[token] = revision
+        branches = branches + token + ' '
+      self.revision_branches[revision] = branches
+
+      # Parse revision of next delta in chain
+      self.match_token('next')
+      next = ''
+      token = self.get_token()
+      if token != ';':
+        next = token
+        self.get_token()         # Eat semicolon
+        self.next_delta[revision] = next
+        self.prev_delta[next] = revision
+        if is_trunk_revision:
+          self.prev_revision[revision] = next
+        else:
+          self.prev_revision[next] = revision
+
+      if self.debug >= 3:
+        print "<pre>revision =", revision
+        print "date     = ", date
+        print "author   = ", author
+        print "branches = ", branches
+        print "next     = ", next + "</pre>\n"
+
+  def parse_rcs_description(self):
+    self.match_token('desc')
+    self.rcs_file_description = self.get_token()
+
+  # Construct associative arrays containing info about individual revisions.
+  #
+  # The following associative arrays are created, keyed by revision number:
+  #   revision_log        -- log message
+  #   revision_deltatext  -- Either the complete text of the revision,
+  #                          in the case of the head revision, or the
+  #                          encoded delta between this revision and another.
+  #                          The delta is either with respect to the successor
+  #                          revision if this revision is on the trunk or
+  #                          relative to its immediate predecessor if this
+  #                          revision is on a branch.
+  def parse_rcs_deltatext(self):
+    while not self.feof:
+      revision = self.get_token()
+      if self.debug >= 3:
+        print "Reading delta for revision:", revision
+      self.match_token('log')
+      self.revision_log[revision] = self.get_token()
+      self.match_token('text')
+      self.revision_deltatext[revision] = self.get_token()
+
+  def parse_rcs_file(self):
+    if self.debug >= 2:
+      print "Reading RCS admin..."
+    self.parse_rcs_admin()
+    if self.debug >= 2:
+      print "Reading RCS revision tree topology..."
+    self.parse_rcs_tree()
+
+    if self.debug >= 3:
+      print "<pre>Keys:\n"
+      for i in self.tag_revision.keys():
+        print "yoyuo %s: %s" % (i, self.tag_revision[i])
+      print "</pre>"
+
+    self.parse_rcs_description()
+    if self.debug >= 2:
+      print "Reading RCS revision deltas..."
+    self.parse_rcs_deltatext()
+    if self.debug >= 2:
+      print "Done reading RCS file..."
+
+  def parse_cvs_file(self, rcs_pathname, opt_rev = None, opt_m_timestamp = None):
+    # Args in:  opt_rev - requested revision
+    #           opt_m - time since modified
+    # Args out: revision_map
+    #           timestamp
+    #           revision_deltatext
+
+    # CheckHidden(rcs_pathname);
+    try:
+      self.rcsfile = open(rcs_pathname, 'r')
+    except:
+      raise RuntimeError, ('error: %s appeared to be under CVS control, ' +
+              'but the RCS file is inaccessible.') % rcs_pathname
+
+    self.parse_rcs_file()
+    self.rcsfile.close()
+
+    if opt_rev in [None, '', 'HEAD']:
+      # Explicitly specified topmost revision in tree
+      revision = self.head_revision
+    else:
+      # Symbolic tag or specific revision number specified.
+      revision = self.map_tag_to_revision(opt_rev)
+      if revision == '':
+        raise RuntimeError, 'error: -r: No such revision: ' + opt_rev
+
+    # The primordial revision is not always 1.1!  Go find it.
+    primordial = revision
+    while self.prev_revision.get(primordial):
+      primordial = self.prev_revision[primordial]
+
+    # Don't display file at all, if -m option is specified and no
+    # changes have been made in the specified file.
+    if opt_m_timestamp and self.timestamp[revision] < opt_m_timestamp:
+      return ''
+
+    # Figure out how many lines were in the primordial, i.e. version 1.1,
+    # check-in by moving backward in time from the head revision to the
+    # first revision.
+    line_count = 0
+    if self.revision_deltatext.get(self.head_revision):
+      tmp_array = string.split(self.revision_deltatext[self.head_revision], '\n')
+      line_count = len(tmp_array)
+
+    skip = 0
+
+    rev = self.prev_revision.get(self.head_revision)
+    while rev:
+      diffs = string.split(self.revision_deltatext[rev], '\n')
+      for command in diffs:
+        dmatch = self.d_command.match(command)
+        amatch = self.a_command.match(command)
+        if skip > 0:
+          # Skip insertion lines from a prior "a" command
+          skip = skip - 1
+        elif dmatch:
+          # "d" - Delete command
+          start_line = string.atoi(dmatch.group(1))
+          count      = string.atoi(dmatch.group(2))
+          line_count = line_count - count
+        elif amatch:
+          # "a" - Add command
+          start_line = string.atoi(amatch.group(1))
+          count      = string.atoi(amatch.group(2))
+          skip       = count;
+          line_count = line_count + count
+        else:
+          raise RuntimeError, 'error: illegal RCS file'
+
+      rev = self.prev_revision.get(rev)
+
+    # Now, play the delta edit commands *backwards* from the primordial
+    # revision forward, but rather than applying the deltas to the text of
+    # each revision, apply the changes to an array of revision numbers.
+    # This creates a "revision map" -- an array where each element
+    # represents a line of text in the given revision but contains only
+    # the revision number in which the line was introduced rather than
+    # the line text itself.
+    #
+    # Note: These are backward deltas for revisions on the trunk and
+    # forward deltas for branch revisions.
+
+    # Create initial revision map for primordial version.
+    self.revision_map = [primordial] * line_count
+
+    ancestors = [revision, ] + self.ancestor_revisions(revision)
+    ancestors = ancestors[:-1]  # Remove "1.1"
+    last_revision = primordial
+    ancestors.reverse()
+    for revision in ancestors:
+      is_trunk_revision = self.trunk_rev.match(revision) is not None
+
+      if is_trunk_revision:
+        diffs = string.split(self.revision_deltatext[last_revision], '\n')
+
+        # Revisions on the trunk specify deltas that transform a
+        # revision into an earlier revision, so invert the translation
+        # of the 'diff' commands.
+        for command in diffs:
+          if skip > 0:
+            skip = skip - 1
+          else:
+            dmatch = self.d_command.match(command)
+            amatch = self.a_command.match(command)
+            if dmatch:
+              start_line = string.atoi(dmatch.group(1))
+              count      = string.atoi(dmatch.group(2))
+              temp = []
+              while count > 0:
+                temp.append(revision)
+                count = count - 1
+              self.revision_map = (self.revision_map[:start_line - 1] +
+                      temp + self.revision_map[start_line - 1:])
+            elif amatch:
+              start_line = string.atoi(amatch.group(1))
+              count      = string.atoi(amatch.group(2))
+              del self.revision_map[start_line:start_line + count]
+              skip = count
+            else:
+              raise RuntimeError, 'Error parsing diff commands'
+
+      else:
+        # Revisions on a branch are arranged backwards from those on
+        # the trunk.  They specify deltas that transform a revision
+        # into a later revision.
+        adjust = 0
+        diffs = string.split(self.revision_deltatext[revision], '\n')
+        for command in diffs:
+          if skip > 0:
+            skip = skip - 1
+          else:
+            dmatch = self.d_command.match(command)
+            amatch = self.a_command.match(command)
+            if dmatch:
+              start_line = string.atoi(dmatch.group(1))
+              count      = string.atoi(dmatch.group(2))
+              del self.revision_map[start_line + adjust - 1:start_line + adjust - 1 + count]
+              adjust = adjust - count
+            elif amatch:
+              start_line = string.atoi(amatch.group(1))
+              count      = string.atoi(amatch.group(2))
+              skip = count
+              temp = []
+              while count > 0:
+                temp.append(revision)
+                count = count - 1
+              self.revision_map = (self.revision_map[:start_line + adjust] +
+                      temp + self.revision_map[start_line + adjust:])
+              adjust = adjust + skip
+            else:
+              raise RuntimeError, 'Error parsing diff commands'
+
+      last_revision = revision
+
+    return revision
+
+
+re_includes = re.compile('\\#(\\s*)include(\\s*)"(.*?)"')
+re_filename = re.compile('(.*[\\\\/])?(.+)')
+
+def link_includes(text, root, rcs_path):
+  match = re_includes.match(text)
+  if match:
+    incfile = match.group(3)
+    for rel_path in ('', 'Attic', '..'):
+      trial_root = os.path.join(rcs_path, rel_path)
+      file = os.path.normpath('%s%s%s%s%s,v' % (root, path_sep, trial_root, path_sep, incfile))
+      if os.access(file, os.F_OK):
+        return '#%sinclude%s"<a href="%s">%s</a>"' % \
+               (match.group(1), match.group(2),
+                os.path.join(rel_path, incfile), incfile)
+  return text
+
+def make_html(root, rcs_path, opt_rev = None):
+  filename = root + path_sep + rcs_path
+  parser = CVSParser()
+  revision = parser.parse_cvs_file(filename, opt_rev)
+  count = len(parser.revision_map)
+  text = parser.extract_revision(revision)
+  if len(text) != count:
+    raise RuntimeError, 'Internal consistency error'
+
+  match = re_filename.match(rcs_path)
+  if not match:
+    raise RuntimeError, 'Unable to parse filename'
+  file_head = match.group(1)
+  file_tail = match.group(2)
+
+  open_table_tag = '<table border=0 cellpadding=0 cellspacing=0 width="100%">'
+  startOfRow = '<tr><td colspan=3%s><pre>'
+  endOfRow = '</td></tr>'
+
+  print open_table_tag + (startOfRow % '')
+
+  if count == 0:
+    count = 1
+
+  line_num_width = int(math.log10(count)) + 1
+  revision_width = 3
+  author_width = 5
+  line = 0
+  usedlog = {}
+  usedlog[revision] = 1
+  old_revision = 0
+  row_color = ''
+  lines_in_table = 0
+  inMark = 0
+  rev_count = 0
+
+  for revision in parser.revision_map:
+    thisline = text[line]
+    line = line + 1
+    usedlog[revision] = 1
+    line_in_table = lines_in_table + 1
+
+    # Escape HTML meta-characters
+    thisline = cgi.escape(thisline)
+
+    # Add a link to traverse to included files
+    if 1:   # opt_includes
+      thisline = link_includes(thisline, root, file_head)
+
+    output = ''
+
+    # Highlight lines
+    #mark_cmd;
+    #if (defined($mark_cmd = $mark_line{$line}) and mark_cmd != 'end':
+    #	output = output + endOfRow + '<tr><td bgcolor=LIGHTGREEN width="100%"><pre>'
+    #	inMark = 1
+
+    if old_revision != revision and line != 1:
+      if row_color == '':
+        row_color = ' bgcolor="#e7e7e7"'
+      else:
+        row_color = ''
+
+      if not inMark:
+        if lines_in_table > 100:
+          output = output + endOfRow + '</table>' + open_table_tag + (startOfRow % row_color)
+          lines_in_table = 0
+        else:
+          output = output + endOfRow + (startOfRow % row_color)
+
+    elif lines_in_table > 200 and not inMark:
+      output = output + endOfRow + '</table>' + open_table_tag + (startOfRow % row_color)
+      lines_in_table = 0
+
+    output = output + "<a name=%d></a>" % (line, )
+    if 1:  # opt_line_nums
+      output = output + ('%%%dd' % (line_num_width, )) % (line, )
+
+    if old_revision != revision or rev_count > 20:
+      revision_width = max(revision_width, len(revision))
+
+      if parser.prev_revision.get(revision):
+        fname = file_tail[:-2]	# strip the ",v"
+        ### need the sticky options! need cvsroot if not-default
+        output = output + ' <a href="%s.diff?r1=%s&amp;r2=%s"' % \
+                 (fname, parser.prev_revision[revision], revision)
+        if 0: # use_layers
+          output = output + " onmouseover='return log(event,\"%s\",\"%s\");'" % (
+                  parser.prev_revision[revision], revision)
+        output = output + ">"
+      else:
+        output = output + " "
+        parser.prev_revision[revision] = ''
+
+      author = parser.revision_author[revision]
+      # $author =~ s/%.*$//;
+      author_width = max(author_width, len(author))
+      output = output + ('%%-%ds ' % (author_width, )) % (author, )
+      output = output + revision
+      if parser.prev_revision.get(revision):
+        output = output + '</a>'
+      output = output + (' ' * (revision_width - len(revision) + 1))
+
+      old_revision = revision
+      rev_count = 0
+    else:
+      output = output + '   ' + (' ' * (author_width + revision_width))
+    rev_count = rev_count + 1
+
+    output = output + thisline
+
+    # Close the highlighted section
+    #if (defined $mark_cmd and mark_cmd != 'begin'):
+    #	chop($output)
+    #	output = output + endOfRow + (startOfRow % row_color)
+    #	inMark = 0
+
+    print output
+  print endOfRow + '</table>'
+
+
+def main():
+  if len(sys.argv) != 3:
+    print 'USAGE: %s cvsroot rcs-file' % sys.argv[0]
+    sys.exit(1)
+  make_html(sys.argv[1], sys.argv[2])
+
+if __name__ == '__main__':
+  main()

lib/commit.py

@@ -0,0 +1,160 @@
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+
+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 +1,67 @@
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+# compat.py: compatibility functions for operation across Python 1.5.x
+#
+# -----------------------------------------------------------------------
+#
+
+import urllib
+import string
+import time
+import re
+import os
+
+
+#
+# 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.'
+
+#
+# os.makedirs() is new to Python 1.5.2
+#
+try:
+  makedirs = os.makedirs
+except AttributeError:
+  def makedirs(path, mode=0777):
+    head, tail = os.path.split(path)
+    if head and tail and not os.path.exists(head):
+      makedirs(head, mode)
+    os.mkdir(path, mode)

lib/config.py

@@ -0,0 +1,274 @@
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+# config.py: configuration utilities
+#
+# -----------------------------------------------------------------------
+#
+
+import sys
+import os
+import string
+import ConfigParser
+import fnmatch
+
+
+#########################################################################
+#
+# 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',
+                        'disable_enscript_lang')
+
+  def __init__(self):
+    for section in self._sections:
+      setattr(self, section, _sub_config())
+
+  def load_config(self, fname, vhost=None):
+    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 parser.has_section(section):
+        self._process_section(parser, section, section)
+
+    if vhost:
+      self._process_vhost(parser, vhost)
+
+  def _process_section(self, parser, section, subcfg_name):
+    sc = getattr(self, subcfg_name)
+
+    for opt in parser.options(section):
+      value = parser.get(section, opt)
+      if opt in self._force_multi_value or subcfg_name == 'images':
+        value = map(string.strip, filter(None, 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 _process_vhost(self, parser, vhost):
+    canon_vhost = self._find_canon_vhost(parser, vhost)
+    if not canon_vhost:
+      # none of the vhost sections matched
+      return
+
+    cv = canon_vhost + '-'
+    lcv = len(cv)
+    for section in parser.sections():
+      if section[:lcv] == cv:
+        self._process_section(parser, section, section[lcv:])
+
+  def _find_canon_vhost(self, parser, vhost):
+    vhost = string.lower(vhost)
+
+    for canon_vhost in parser.options('vhosts'):
+      value = parser.get('vhosts', canon_vhost)
+      patterns = map(string.lower, map(string.strip,
+                                       filter(None, string.split(value, ','))))
+      for pat in patterns:
+        if fnmatch.fnmatchcase(vhost, pat):
+          return canon_vhost
+
+    return None
+
+  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.options.use_enscript = 0
+    self.options.enscript_path = ''
+    self.options.disable_enscript_lang = ()
+
+    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>
+    """
+
+  def is_forbidden(self, module):
+    if not module:
+      return 0
+    default = 0
+    for pat in self.general.forbidden:
+      if pat[0] == '!':
+        default = 1
+        if fnmatch.fnmatchcase(module, pat[1:]):
+          return 0
+      elif fnmatch.fnmatchcase(module, pat):
+        return 1
+    return default
+
+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 +1,136 @@
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+
+#########################################################################
+#
+# INSTALL-TIME CONFIGURATION
+#
+# These values will be set during the installation process. During
+# development, they will remain None.
+#
+
+CONF_PATHNAME = None
+
+#########################################################################
+
+import os, database, rlog, commit, config
+
+## 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
+
+## load configuration file, the data is used globally here
+cfg = config.Config()
+cfg.set_defaults()
+cfg.load_config(CONF_PATHNAME)
+
+
+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 +1,476 @@
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+
+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/dbi.py

@@ -0,0 +1,71 @@
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+
+import sys
+import MySQLdb
+
+
+dbi_error = "dbi error"
+
+
+## make some checks in MySQLdb
+_no_datetime = """\
+ERROR: Your version of MySQLdb requires the mxDateTime module
+       for the Timestamp() and TimestampFromTicks() methods.
+       You will need to install mxDateTime to use the ViewCVS
+       database.
+"""
+
+if not hasattr(MySQLdb, "Timestamp") or \
+   not hasattr(MySQLdb, "TimestampFromTicks"):
+    sys.stderr.write(_no_datetime)
+    sys.exit(1)
+
+
+class Cursor:
+    def __init__(self, mysql_cursor):
+        self.__cursor = mysql_cursor
+
+    def execute(self, *args):
+        apply(self.__cursor.execute, args)
+
+    def fetchone(self):
+        try:
+            row = self.__cursor.fetchone()
+        except IndexError:
+            row = None
+        
+        return row
+    
+
+class Connection:
+    def __init__(self, host, user, passwd, db):
+        self.__mysql = MySQLdb.connect(
+            host=host, user=user, passwd=passwd, db=db)
+
+    def cursor(self):
+        return Cursor(self.__mysql.cursor())
+
+
+def Timestamp(year, month, date, hour, minute, second):
+    return MySQLdb.Timestamp(year, month, date, hour, minute, second)
+
+
+def TimestampFromTicks(ticks):
+    return MySQLdb.TimestampFromTicks(ticks)
+
+
+def connect(host, user, passwd, db):
+    return Connection(host, user, passwd, db)

lib/popen.py

@@ -0,0 +1,90 @@
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+# popen.py: a replacement for os.popen()
+#
+# This implementation of popen() provides a cmd + args calling sequence,
+# rather than a system() type of convention. The shell facilities are not
+# available, but that implies we can avoid worrying about shell hacks in
+# the arguments.
+#
+# -----------------------------------------------------------------------
+#
+
+import os
+
+def popen(cmd, args, mode, capture_err=1):
+  r, w = os.pipe()
+  pid = os.fork()
+  if pid:
+    # in the parent
+
+    # close the descriptor that we don't need and return the other one.
+    if mode == 'r':
+      os.close(w)
+      return _pipe(os.fdopen(r, 'r'), pid)
+    os.close(r)
+    return _pipe(os.fdopen(w, 'w'), pid)
+
+  # in the child
+
+  # we'll need /dev/null for the discarded I/O
+  null = os.open('/dev/null', os.O_RDWR)
+
+  if mode == 'r':
+    # hook stdout/stderr to the "write" channel
+    os.dup2(w, 1)
+    # "close" stdin; the child shouldn't use it
+    os.dup2(null, 0)
+    # what to do with errors?
+    if capture_err:
+      os.dup2(w, 2)
+    else:
+      os.dup2(null, 2)
+  else:
+    # hook stdin to the "read" channel
+    os.dup2(r, 0)
+    # "close" stdout/stderr; the child shouldn't use them
+    os.dup2(null, 1)
+    os.dup2(null, 2)
+
+  # don't need these FDs any more
+  os.close(null)
+  os.close(r)
+  os.close(w)
+
+  # the stdin/stdout/stderr are all set up. exec the target
+  os.execvp(cmd, (cmd,) + tuple(args))
+
+  # crap. shouldn't be here.
+  sys.exit(127)
+
+
+class _pipe:
+  "Wrapper for a file which can wait() on a child process at close time."
+
+  def __init__(self, file, child_pid):
+    self.file = file
+    self.child_pid = child_pid
+
+  def close(self):
+    self.file.close()
+    self.file = None
+    return os.waitpid(self.child_pid, 0)[1] or None
+
+  def __getattr__(self, name):
+    return getattr(self.file, name)
+
+  def __del__(self):
+    if self.file:
+      self.close()

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/query.py

@@ -0,0 +1,102 @@
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+
+import time
+import dbi
+
+
+## QueryEntry holds data on one match-type in the SQL database
+## match is: "exact", "like", or "regex"
+
+class QueryEntry:
+    def __init__(self, data, match):
+        self.data = data
+        self.match = match
+
+
+## CheckinDatabaseQueryData is a object which contains the search parameters
+## for a query to the CheckinDatabase
+        
+class CheckinDatabaseQuery:
+    def __init__(self):
+        ## sorting
+        self.sort = "date"
+        
+        ## repository to query
+        self.repository_list = []
+        self.branch_list = []
+        self.directory_list = []
+        self.file_list = []
+        self.author_list = []
+
+        ## 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, match = "exact"):
+        self.repository_list.append(QueryEntry(repository, match))
+
+    def SetBranch(self, branch, match = "exact"):
+        self.branch_list.append(QueryEntry(branch, match))
+
+    def SetDirectory(self, directory, match = "exact"):
+        self.directory_list.append(QueryEntry(directory, match))
+
+    def SetFile(self, file, match = "exact"):
+        self.file_list.append(QueryEntry(file, match))
+
+    def SetAuthor(self, author, match = "exact"):
+        self.author_list.append(QueryEntry(author, match))
+
+    def SetSortMethod(self, sort):
+        self.sort = sort
+
+    def SetFromDateObject(self, ticks):
+        self.from_date = dbi.TimestampFromTicks(ticks)
+
+    def SetToDateObject(self, ticks):
+        self.to_date = dbi.TimestampFromTicks(ticks)
+
+    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 CreateCheckinQuery():
+    return CheckinDatabaseQuery()

lib/rlog.py

@@ -0,0 +1,348 @@
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+
+#########################################################################
+#
+# INSTALL-TIME CONFIGURATION
+#
+# These values will be set during the installation process. During
+# development, they will remain None.
+#
+
+CONF_PATHNAME = None
+
+#########################################################################
+
+import os, sys, string, re, time, config
+
+## load configuration file, the data is used globally here
+cfg = config.Config()
+cfg.set_defaults()
+cfg.load_config(CONF_PATHNAME)
+
+
+## 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))
+
+        temp = os.path.join(cfg.general.rcs_path, "rlog")
+        self.cmd = '%s %s "%s"' % (temp, 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 +1,161 @@
+#!/usr/bin/env python
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+# administrative program for CVSdb; this is primarily
+# used to add/rebuild CVS repositories to the database
+#
+# -----------------------------------------------------------------------
+#
+
+#########################################################################
+#
+# INSTALL-TIME CONFIGURATION
+#
+# These values will be set during the installation process. During
+# development, they will remain None.
+#
+
+LIBRARY_DIR = None
+CONF_PATHNAME = None
+
+# Adjust sys.path to include our library directory
+import sys
+
+if LIBRARY_DIR:
+  sys.path.insert(0, LIBRARY_DIR)
+else:
+  sys.path[:0] = ['../lib']	# any other places to look?
+
+#########################################################################
+  
+import os, string, 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 +1,187 @@
+#!/usr/bin/python
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+# updates SQL database with new commit records
+#
+# -----------------------------------------------------------------------
+#
+
+#########################################################################
+#
+# INSTALL-TIME CONFIGURATION
+#
+# These values will be set during the installation process. During
+# development, they will remain None.
+#
+
+LIBRARY_DIR = None
+CONF_PATHNAME = None
+
+# Adjust sys.path to include our library directory
+import sys
+
+if LIBRARY_DIR:
+  sys.path.insert(0, LIBRARY_DIR)
+else:
+  sys.path[:0] = ['../lib']	# any other places to look?
+
+#########################################################################
+
+import os, string, 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')
+            return
+
+    ## 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)

tools/make-database

@@ -0,0 +1,146 @@
+#!/usr/bin/env python
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+# administrative program for CVSdb; creates a clean database in
+# MySQL 3.22 or later
+#
+# -----------------------------------------------------------------------
+#
+import os, sys, string
+
+INTRO_TEXT = """\
+This script creates the database and tables in MySQL used by the ViewCVS
+checkin database.  You will be prompted for: database user, database user
+password, and database name.  This script will use mysql to create the
+database for you.  You will then need to set the appropriate parameters
+in your viewcvs.conf file under the [cvsdb] section.
+"""
+
+DATABASE_SCRIPT="""\
+DROP DATABASE IF EXISTS <dbname>;
+CREATE DATABASE <dbname>;
+
+USE <dbname>;
+
+DROP TABLE IF EXISTS branches;
+CREATE TABLE branches (
+  id mediumint(9) DEFAULT '0' NOT NULL auto_increment,
+  branch varchar(64) binary DEFAULT '' NOT NULL,
+  PRIMARY KEY (id),
+  UNIQUE branch (branch)
+);
+
+DROP TABLE IF EXISTS checkins;
+CREATE TABLE checkins (
+  type enum('Change','Add','Remove'),
+  ci_when datetime DEFAULT '0000-00-00 00:00:00' NOT NULL,
+  whoid mediumint(9) DEFAULT '0' NOT NULL,
+  repositoryid mediumint(9) DEFAULT '0' NOT NULL,
+  dirid mediumint(9) DEFAULT '0' NOT NULL,
+  fileid mediumint(9) DEFAULT '0' NOT NULL,
+  revision varchar(32) binary DEFAULT '' NOT NULL,
+  stickytag varchar(255) binary DEFAULT '' NOT NULL,
+  branchid mediumint(9) DEFAULT '0' NOT NULL,
+  addedlines int(11) DEFAULT '0' NOT NULL,
+  removedlines int(11) DEFAULT '0' NOT NULL,
+  descid mediumint(9),
+  UNIQUE repositoryid (repositoryid,dirid,fileid,revision),
+  KEY ci_when (ci_when),
+  KEY whoid (whoid),
+  KEY repositoryid_2 (repositoryid),
+  KEY dirid (dirid),
+  KEY fileid (fileid),
+  KEY branchid (branchid)
+);
+
+DROP TABLE IF EXISTS descs;
+CREATE TABLE descs (
+  id mediumint(9) DEFAULT '0' NOT NULL auto_increment,
+  description text,
+  hash bigint(20) DEFAULT '0' NOT NULL,
+  PRIMARY KEY (id),
+  KEY hash (hash)
+);
+
+DROP TABLE IF EXISTS dirs;
+CREATE TABLE dirs (
+  id mediumint(9) DEFAULT '0' NOT NULL auto_increment,
+  dir varchar(128) binary DEFAULT '' NOT NULL,
+  PRIMARY KEY (id),
+  UNIQUE dir (dir)
+);
+
+DROP TABLE IF EXISTS files;
+CREATE TABLE files (
+  id mediumint(9) DEFAULT '0' NOT NULL auto_increment,
+  file varchar(128) binary DEFAULT '' NOT NULL,
+  PRIMARY KEY (id),
+  UNIQUE file (file)
+);
+
+DROP TABLE IF EXISTS people;
+CREATE TABLE people (
+  id mediumint(9) DEFAULT '0' NOT NULL auto_increment,
+  who varchar(32) binary DEFAULT '' NOT NULL,
+  PRIMARY KEY (id),
+  UNIQUE who (who)
+);
+
+DROP TABLE IF EXISTS repositories;
+CREATE TABLE repositories (
+  id mediumint(9) DEFAULT '0' NOT NULL auto_increment,
+  repository varchar(64) binary DEFAULT '' NOT NULL,
+  PRIMARY KEY (id),
+  UNIQUE repository (repository)
+);
+
+DROP TABLE IF EXISTS tags;
+CREATE TABLE tags (
+  repositoryid mediumint(9) DEFAULT '0' NOT NULL,
+  branchid mediumint(9) DEFAULT '0' NOT NULL,
+  dirid mediumint(9) DEFAULT '0' NOT NULL,
+  fileid mediumint(9) DEFAULT '0' NOT NULL,
+  revision varchar(32) binary DEFAULT '' NOT NULL,
+  UNIQUE repositoryid (repositoryid,dirid,fileid,branchid,revision),
+  KEY repositoryid_2 (repositoryid),
+  KEY dirid (dirid),
+  KEY fileid (fileid),
+  KEY branchid (branchid)
+);
+"""
+
+if __name__ == "__main__":
+    print INTRO_TEXT
+    
+    user = raw_input("MySQL User: ")
+    passwd = raw_input("MySQL Password: ")
+    dbase = raw_input("ViewCVS Database Name [default: ViewCVS]: ")
+    if not dbase:
+        dbase = "ViewCVS"
+
+    cmd = "{ mysql --user=%s --password=%s ; } 2>&1" % (user, passwd)
+    dscript = string.replace(DATABASE_SCRIPT, "<dbname>", dbase)
+    
+    mysql = os.popen(cmd, "w")
+    mysql.write(dscript)
+    status = mysql.close()
+
+    if status:
+        print "[ERROR] the database did not create sucessfully."
+        sys.exit(1)
+
+    print "Database created successfully."
+    sys.exit(0)
+    

tools/make-release

@@ -0,0 +1,39 @@
+#!/bin/sh
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+# make-release: internal tool for creating ViewCVS releases
+#
+# -----------------------------------------------------------------------
+#
+
+if [ "x$1" = "x" ]; then
+  echo "USAGE: $0 target-directory"
+  exit 1
+fi
+
+# grab a copy of the CVS repository  (export requires a tag, so just use 'co')
+rm -r $1
+echo 'Checking out into:' $1
+cvs -d /home/cvsroot co -d $1 -kv -P -R viewcvs
+
+echo 'Cleaning up...'
+# clean out the CVS crap
+find $1 -name CVS | xargs rm -r
+
+# various shifting, cleanup
+mv $1/website/license-1.html $1/LICENSE.html
+rm -r $1/website
+rm $1/tools/make-release
+
+echo 'Done.'

viewcvs-install

@@ -0,0 +1,176 @@
+#!/usr/bin/env python
+# -*- Mode: python -*-
+#
+# Copyright (C) 2000 The ViewCVS Group. All Rights Reserved.
+#
+# By using this file, you agree to the terms and conditions set forth in
+# the LICENSE.html file which can be found at the top level of the ViewCVS
+# distribution or at http://www.lyra.org/viewcvs/license-1.html.
+#
+# Contact information:
+#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
+#   gstein@lyra.org, http://www.lyra.org/viewcvs/
+#
+# -----------------------------------------------------------------------
+#
+# install script for viewcvs -- temporary?
+#
+# ### this will eventually be replaced by autoconf plus tools. an
+# ### interactive front-end to ./configure may be provided.
+#
+# -----------------------------------------------------------------------
+#
+
+import os
+import sys
+import string
+import re
+import traceback
+import py_compile
+
+# get access to our library modules
+sys.path.insert(0, os.path.join(os.path.dirname(sys.argv[0]), 'lib'))
+
+import compat
+
+
+## installer text
+INFO_TEXT = """\
+
+This is the ViewCVS installer.  It will allow you to choose the install
+path for ViewCVS.  You will now be asked some installation questions.
+Defaults are given in square brackets.  Just hit [Enter] if a default
+is okay.
+"""
+
+## installer defaults
+ROOT_DIR = "/usr/local/viewcvs"
+
+
+## list of files for installation
+## tuple (source path, destination path, install mode, true/false flag for
+##        search-and-replace, flag for prompt before replace, compile_it)
+##       
+
+FILE_INFO_LIST = [
+    ("cgi/viewcvs.cgi", "cgi/viewcvs.cgi", 0755, 1, 0, 0),
+    ("cgi/queryform.cgi", "cgi/queryform.cgi", 0755, 1, 0, 0),
+    ("cgi/query.cgi", "cgi/query.cgi", 0755, 1, 0, 0),
+
+    ("cgi/viewcvs.conf.dist", "viewcvs.conf", 0644, 0, 1, 0),
+
+    ("lib/PyFontify.py", "lib/PyFontify.py", 0644, 0, 0, 1),
+    ("lib/blame.py", "lib/blame.py", 0644, 0, 0, 1),
+    ("lib/commit.py", "lib/commit.py", 0644, 0, 0, 1),
+    ("lib/compat.py", "lib/compat.py", 0644, 0, 0, 1),
+    ("lib/config.py", "lib/config.py", 0644, 0, 0, 1),
+    ("lib/cvsdbapi.py", "lib/cvsdbapi.py", 0644, 1, 0, 1),
+    ("lib/database.py", "lib/database.py", 0644, 0, 0, 1),
+    ("lib/popen.py", "lib/popen.py", 0644, 0, 0, 1),
+    ("lib/py2html.py", "lib/py2html.py", 0644, 0, 0, 1),
+    ("lib/rlog.py", "lib/rlog.py", 0644, 1, 0, 1),
+    
+    ("tools/loginfo-handler", "loginfo-handler", 0755, 1, 0, 0),
+    ("tools/cvsdbadmin", "cvsdbadmin", 0755, 1, 0, 0),
+    ("tools/make-database", "make-database", 0755, 1, 0, 0),
+
+    ("html-templates/queryformtemplate.html",
+     "html-templates/queryformtemplate.html", 0644, 0, 1, 0),
+    ("html-templates/querytemplate.html",
+     "html-templates/querytemplate.html", 0644, 0, 1, 0),
+    ]
+
+
+def Error(text, etype=None, evalue=None):
+    print
+    print "[ERROR] %s" % text
+    if etype:
+        print '[ERROR] ',
+        traceback.print_exception(etype, evalue, None, file=sys.stdout)
+    sys.exit(1)
+    
+
+def MkDir(path):
+    try:
+        compat.makedirs(path)
+    except OSError, e:
+        if e.errno == 17:
+            # EEXIST: file exists
+            return
+        if e.errno == 13:
+            # EACCES: permission denied
+            Error("You do not have permission to create directory %s" % path)
+        Error("Unknown error creating directory %s" % path, OSError, e)
+
+
+
+def SetOnePath(contents, var, value):
+    pattern = re.compile('^' + var + r'\s*=\s*.*$', re.MULTILINE)
+    repl = '%s = "%s"' % (var, os.path.join(ROOT_DIR, value))
+    return re.sub(pattern, repl, contents)
+
+def SetPythonPaths(contents):
+    if contents[:2] == '#!':
+        shbang = '#!' + sys.executable
+        contents = re.sub('^#![^\n]*', shbang, contents)
+    contents = SetOnePath(contents, 'LIBRARY_DIR', 'lib')
+    contents = SetOnePath(contents, 'CONF_PATHNAME', 'viewcvs.conf')
+    contents = SetOnePath(contents, 'HTML_TEMPLATE_DIR', 'html-templates')
+    return contents
+
+
+def InstallFile(src_path, dest_path, mode, set_python_paths, prompt_replace,
+                compile_it):
+    dest_path = os.path.join(ROOT_DIR, dest_path)
+    
+    if prompt_replace and os.path.exists(dest_path):
+        temp = raw_input("File %s exists, overwright? [y/N]: " % (dest_path))
+        if not temp or string.lower(temp[0]) != "y":
+            return
+    
+    try:
+        contents = open(src_path, "r").read()
+    except IOError, e:
+        Error(str(e))
+
+    if set_python_paths:
+        contents = SetPythonPaths(contents)
+
+    ## write the file to the destination location
+    path, basename = os.path.split(dest_path)
+    MkDir(path)
+
+    try:
+        open(dest_path, "w").write(contents)
+    except IOError, e:
+        if e.errno == 13:
+            # EACCES: permission denied
+            Error("You do not have permission to write file %s" % dest_path)
+        Error("Unknown error writing file %s" % dest_path, IOError, e)
+        
+    os.chmod(dest_path, mode)
+
+    if compile_it:
+      py_compile.compile(dest_path)
+
+
+## MAIN
+if __name__ == "__main__":
+    print INFO_TEXT
+    
+    ## get the install path
+    temp = raw_input("Installation Path [%s]: " % ROOT_DIR)
+    temp = string.strip(temp)
+    if len(temp):
+        ROOT_DIR = temp
+        
+    ## install the files
+    print
+    print "Installing ViewCVS to:", ROOT_DIR
+
+    for args in FILE_INFO_LIST:
+        print "        ", args[0]
+        apply(InstallFile, args)
+
+    print
+    print "Installation Complete"

website/index.html

@@ -19,41 +19,40 @@
     <p>
       ViewCVS can browse directories, change logs, and specific
       revisions of files. It can display diffs between versions and
-      show selections of files based on tags or branches.
+      show selections of files based on tags or branches. In addition, 
+      ViewCVS has "annotation" or "blame" support, and the beginnings
+      of Bonsai-like query facilities.
     </p>
     <p>
-      ViewCVS is currently at version 0.3. It is almost a straight
-      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 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 
-      Bad Thing to do. One of my tasks will be eliminating the
-      read/write requirement.
+      ViewCVS is currently at version 0.5. 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 minor
+      "badness" in there, but I've been working on flushing that out,
+      while adding new features. Currently, the functionality of ViewCVS
+      surpasses that of cvsweb.
     </p>
     <p>
       The software is available for download:
     </p>
     <blockquote>
-      <a href="viewcvs-0.3.tar.gz">Version 0.3 of ViewCVS</a>
+      <a href="viewcvs-0.5.tar.gz">Version 0.5 of ViewCVS</a>
     </blockquote>
     <p>
       Of course, it is also available through ViewCVS itself:
     </p>
     <blockquote>
-      <a href="/cgi-bin/viewcvs.cgi/gjspy/viewcvs/">http://www.lyra.org/cgi-bin/viewcvs.cgi/gjspy/viewcvs/</a>
+      <a href="/cgi-bin/viewcvs.cgi/viewcvs/">http://www.lyra.org/cgi-bin/viewcvs.cgi/viewcvs/</a>
     </blockquote>
 
     <p>
-      ViewCVS <font color=red>requires <strong>Python
-	1.5.2</strong></font>.
+      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>
-      [ <a href="../">up to Python software</a> ]
-      [ <a href="../../">up to Greg's page</a> ]
+      [ <a href="/greg/">Greg's page</a> ]
+      [ <a href="/greg/python/">other Python software</a> ]
     </p>
 
     <hr width="75&#37;">
@@ -65,56 +64,51 @@
       <a href="http://mailman.lyra.org/mailman/listinfo/viewcvs">ViewCVS
 	mailing list</a>.
     </p>
-
-    <hr width="75&#37;">
-    <h2>FAQ</h2>
-
-    <p>Kinda short :-)</p>
-
-    <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>
+      A <a href="http://mailman.lyra.org/mailman/listinfo/viewcvs-dev">mailing
+	list for ViewCVS developers</a> is also available. 
+    </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>Colorization for many file types via <code>enscript</code>.</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>
+      <li>Bonsai-like query features.</li>
+      <li>
+	Annotation/blame support against a <strong>read-only</strong>
+	repository.
+      </li>
+      <li>
+	Configuration on a per-virtual-host basis. This allows you
+	to share the configuration file and ViewCVS installation
+	across virtual hosts, yet still be able to fine-tune the
+	options when necessary.
+      </li>
     </ul>
 
     <p>
       Future features, coming soon:
     </p>
     <ul>
-      <li>
-	Optional, separate configuration file (similar to
-	cvsweb). This will make upgrading easier.
-      </li>
       <li>UI streamlining/simplification</li>
       <li>Integration with CVS checkin auto-mail scripts</li>
+      <li>Tighter integration the query features</li>
       <li>
 	<i>Suggestions? Send mail to the
 	  <a href="mailto:viewcvs@lyra.org">viewcvs@lyra.org</a>
@@ -127,20 +121,35 @@ AttributeError: urlencode
       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>
+    <h2>Colorization of files</h2>
+    <p>
+      ViewCVS can make use of the <code>enscript</code> program to
+      colorize files in the CVS repository. If <code>enscript</code>
+      is present on your system, then set the
+      <code>use_enscript</code> option in the
+      <code>viewcvs.conf</code> configuration file. If necessary,
+      update the <code>enscript_path</code> option to point to your
+      installation directory. ... That's it! Now, as you view files
+      through ViewCVS, they will be colored.
+    </p>
 
+    <h3>Colorization of Python files</h3>
+
+    <p>
+      ViewCVS currently comes with a builtin colorizer for Python
+      source files. This may go away, given the new
+      <code>enscript</code> support...
+    </p>
     <p>
       Christophe Pelte suggested this feature: colorize Python source
       files using
-      <a href="http://starship.python.net/crew/lemburg/SoftwareDescriptions.html#py2html.py">py2html</a>
+      <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">PyFontify</a>
+      <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
@@ -152,7 +161,7 @@ AttributeError: urlencode
     <address><a href="mailto:gstein@lyra.org">Greg Stein</a></address>
 <!-- Created: Fri Dec  3 02:51:37 PST 1999 -->
 <!-- hhmts start -->
-Last modified: Fri Feb 11 07:51:53 PST 2000
+Last modified: Fri May 12 03:53:51 PDT 2000
 <!-- hhmts end -->
   </body>
 </html>

website/license-1.html

@@ -0,0 +1,75 @@
+<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML//EN">
+<html>
+  <head>
+    <title>ViewCVS License Agreement (v1)</title>
+  </head>
+
+  <body>
+    <h1>ViewCVS License Agreement (v1)</h1>
+
+    <p>
+      The following text constitutes the license agreement for the
+      <a href="./">ViewCVS</a> software. It
+      is an agreement between
+      <a href="who.html">The ViewCVS
+	Group</a> and the users of ViewCVS.
+    </p>
+
+    <hr>
+
+    <p>
+      <b>
+	Copyright &copy; 1999-2000 The ViewCVS Group.  All rights reserved.
+      </b>
+    </p>
+    <p>
+      By using ViewCVS, you agree to the terms and conditions set
+      forth below:
+    </p>
+    <p>
+      Redistribution and use in source and binary forms, with or
+      without modification, are permitted provided that the following
+      conditions are met:
+    </p>
+    <ol>
+      <li>
+	<p>
+	  Redistributions of source code must retain the above
+	  copyright notice, this list of conditions and the following
+	  disclaimer.
+	</p>
+      </li>
+      <li>
+	<p>
+	  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.
+	</p>
+      </li>
+    </ol>
+
+    <p>
+      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.
+    </p>
+
+    <hr>
+    <address><a href="mailto:gstein@lyra.org">Greg Stein</a></address>
+<!-- Created: Mon May  8 19:01:27 PDT 2000 -->
+<!-- hhmts start -->
+Last modified: Mon May  8 19:28:37 PDT 2000
+<!-- hhmts end -->
+  </body>
+</html>

website/who.html

@@ -0,0 +1,32 @@
+<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML//EN">
+<html>
+  <head>
+    <title>The ViewCVS Group</title>
+  </head>
+
+  <body background="/images/chalk.jpg">
+    <h1>The ViewCVS Group</h1>
+
+    <p>
+      The ViewCVS Group is an informal group of people working on and
+      developing the ViewCVS package. The current set of members are:
+    </p>
+    <ul>
+      <li><a href="/greg/"><b>Greg Stein</b></a></li>
+      <li>Jay Painter</li>
+    </ul>
+
+    <p>
+      Please note that the <a href="./">ViewCVS</a> package is offered 
+      under a BSD-type license, which is detailed on the
+      <a href="license-1.html">ViewCVS License</a> page.
+    </p>
+
+    <hr>
+    <address><a href="mailto:gstein@lyra.org">Greg Stein</a></address>
+<!-- Created: Mon May  8 19:08:58 PDT 2000 -->
+<!-- hhmts start -->
+Last modified: Mon May  8 19:14:45 PDT 2000
+<!-- hhmts end -->
+  </body>
+</html>