Implemented whoosh index building as paster command.

docs update
fixed manifest.in for missing yui file.
Fixed setup to beta
added base for paster upgrade-db command

MANIFEST.in

@@ -1,15 +1,15 b''
 include rhodecode/config/deployment.ini_tmpl
 
 include README.rst
 recursive-include rhodecode/i18n/ *
 
 #images
 recursive-include rhodecode/public/css *
 recursive-include rhodecode/public/images *
 #js
-include rhodecode/public/js/yui2.js
+include rhodecode/public/js/yui2a.js
 include rhodecode/public/js/excanvas.min.js
 include rhodecode/public/js/yui.flot.js
 include rhodecode/public/js/graph.js
 #templates
 recursive-include rhodecode/templates *

development.ini

@@ -1,174 +1,175 b''
 ################################################################################
 ################################################################################
 # rhodecode - Pylons environment configuration                                 #
 #                                                                              # 
 # The %(here)s variable will be replaced with the parent directory of this file#
 ################################################################################
 
 [DEFAULT]
 debug = true
 ################################################################################
 ## Uncomment and replace with the address which should receive                ## 
 ## any error reports after application crash								  ##
 ## Additionally those settings will be used by rhodecode mailing system       ##
 ################################################################################
 #email_to = admin@localhost
 #error_email_from = paste_error@localhost
 #app_email_from = rhodecode-noreply@localhost
 #error_message =
 
 #smtp_server = mail.server.com
 #smtp_username = 
 #smtp_password =
 #smtp_port = 
 #smtp_use_tls = 
 
 [server:main]
 ##nr of threads to spawn
 threadpool_workers = 5
 
 ##max request before
 threadpool_max_requests = 6
 
 ##option to use threads of process
 use_threadpool = false
 
 use = egg:Paste#http
 host = 127.0.0.1
 port = 5000
 
 [app:main]
 use = egg:rhodecode
 full_stack = true
 static_files = true
 lang=en
 cache_dir = %(here)s/data
+index_dir = %(here)s/data/index
 
 ####################################
 ###         BEAKER CACHE        ####
 ####################################
 beaker.cache.data_dir=/%(here)s/data/cache/data
 beaker.cache.lock_dir=/%(here)s/data/cache/lock
 beaker.cache.regions=super_short_term,short_term,long_term,sql_cache_short,sql_cache_med,sql_cache_long
 
 beaker.cache.super_short_term.type=memory
 beaker.cache.super_short_term.expire=10
 
 beaker.cache.short_term.type=memory
 beaker.cache.short_term.expire=60
 
 beaker.cache.long_term.type=memory
 beaker.cache.long_term.expire=36000
 
 
 beaker.cache.sql_cache_short.type=memory
 beaker.cache.sql_cache_short.expire=5
 
 beaker.cache.sql_cache_med.type=memory
 beaker.cache.sql_cache_med.expire=360
 
 beaker.cache.sql_cache_long.type=file
 beaker.cache.sql_cache_long.expire=3600
 
 ####################################
 ###       BEAKER SESSION        ####
 ####################################
 ## Type of storage used for the session, current types are 
 ## "dbm", "file", "memcached", "database", and "memory". 
 ## The storage uses the Container API 
 ##that is also used by the cache system.
 beaker.session.type = file
 
 beaker.session.key = rhodecode
 beaker.session.secret = g654dcno0-9873jhgfreyu
 beaker.session.timeout = 36000
 
 ##auto save the session to not to use .save()
 beaker.session.auto = False
 
 ##true exire at browser close
 #beaker.session.cookie_expires = 3600
 
     
 ################################################################################
 ## WARNING: *THE LINE BELOW MUST BE UNCOMMENTED ON A PRODUCTION ENVIRONMENT*  ##
 ## Debug mode will enable the interactive debugging tool, allowing ANYONE to  ##
 ## execute malicious code after an exception is raised.                       ##
 ################################################################################
 #set debug = false
 
 ##################################
 ###       LOGVIEW CONFIG       ###
 ##################################
 logview.sqlalchemy = #faa
 logview.pylons.templating = #bfb
 logview.pylons.util = #eee
 
 #########################################################
 ### DB CONFIGS - EACH DB WILL HAVE IT'S OWN CONFIG    ###
 #########################################################
 sqlalchemy.db1.url = sqlite:///%(here)s/rhodecode.db
 #sqlalchemy.db1.echo = False
 #sqlalchemy.db1.pool_recycle = 3600
 sqlalchemy.convert_unicode = true
 
 ################################
 ### LOGGING CONFIGURATION   ####
 ################################
 [loggers]
 keys = root, routes, rhodecode, sqlalchemy
 
 [handlers]
 keys = console
 
 [formatters]
 keys = generic,color_formatter
 
 #############
 ## LOGGERS ##
 #############
 [logger_root]
 level = NOTSET
 handlers = console
 
 [logger_routes]
 level = DEBUG
 handlers = console
 qualname = routes.middleware
 # "level = DEBUG" logs the route matched and routing variables.
 propagate = 0
 
 [logger_rhodecode]
 level = DEBUG
 handlers = console
 qualname = rhodecode
 propagate = 0
 
 [logger_sqlalchemy]
 level = ERROR
 handlers = console
 qualname = sqlalchemy.engine
 propagate = 0
 
 ##############
 ## HANDLERS ##
 ##############
 
 [handler_console]
 class = StreamHandler
 args = (sys.stderr,)
 level = NOTSET
 formatter = color_formatter
 
 ################
 ## FORMATTERS ##
 ################
 
 [formatter_generic]
 format = %(asctime)s.%(msecs)03d %(levelname)-5.5s [%(name)s] %(message)s
 datefmt = %Y-%m-%d %H:%M:%S
 
 [formatter_color_formatter]
 class=rhodecode.lib.colored_formatter.ColorFormatter
 format= %(asctime)s.%(msecs)03d %(levelname)-5.5s [%(name)s] %(message)s
 datefmt = %Y-%m-%d %H:%M:%S
  No newline at end of file

docs/changelog.rst

@@ -1,68 +1,69 b''
 .. _changelog:
 
 Changelog
 =========
 
 1.1.0 (**2010-XX-XX**)
 ----------------------
 - git support with push/pull via RhodeCode web interface
 - rewrite of internals for vcs >=0.1.9
 - anonymous access
 - performance upgrade for cached repos list - each repository has it's own 
   cache that's invalidated when needed.
 - main page quick filter for filtering repositories
 - more detailed action logger (based on hooks) with pushed changesets lists
   and options to disable those hooks from admin panel
 - a lot of fixes and tweaks for file browser
 - introduced new enhanced changelog for merges that shows more accurate results
 - gui optimizations, fixed application width to 1024px
 - numerous small bugfixes
+- whoosh index moved to paster command
 
 1.0.2 (**2010-11-12**)
 ----------------------
 
 - fixed #59 missing graph.js
 - fixed repo_size crash when repository had broken symlinks
 - fixed python2.5 crashes.
 - tested under python2.7
 - bumped sqlalchemy and celery versions
 
 1.0.1 (**2010-11-10**)
 ----------------------
 
 - fixed #53 python2.5 incompatible enumerate calls
 - fixed #52 disable mercurial extension for web
 - fixed #51 deleting repositories don't delete it's dependent objects
 - small css updated
 
 1.0.0 (**2010-11-02**)
 ----------------------
 
 - security bugfix simplehg wasn't checking for permissions on commands
   other than pull or push.
 - fixed doubled messages after push or pull in admin journal
 - templating and css corrections, fixed repo switcher on chrome, updated titles
 - admin menu accessible from options menu on repository view
 - permissions cached queries
 
 1.0.0rc4  (**2010-10-12**)
 --------------------------
 
 - fixed python2.5 missing simplejson imports (thanks to Jens Bäckman)
 - removed cache_manager settings from sqlalchemy meta
 - added sqlalchemy cache settings to ini files
 - validated password length and added second try of failure on paster setup-app
 - fixed setup database destroy prompt even when there was no db
 
 
 1.0.0rc3 (**2010-10-11**)
 -------------------------
 
 - fixed i18n during installation.
 
 1.0.0rc2 (**2010-10-11**)
 -------------------------
 
 - Disabled dirsize in file browser, it's causing nasty bug when dir renames 
   occure. After vcs is fixed it'll be put back again.
 - templating/css rewrites, optimized css.

docs/setup.rst

@@ -1,129 +1,148 b''
 .. _setup:
 
 Setup
 =====
 
 
 Setting up the application
 --------------------------
 
 ::
  
  paster make-config RhodeCode production.ini
 
 - This will create `production.ini` config inside the directory
   this config contain various settings for rhodecode, e.g port, email settings
   static files, cache and logging.
 
 ::
 
  paster setup-app production.ini
 
 - This command will create all needed tables and an admin account. 
   When asked for a path You can either use a new location of one with already 
   existing ones. RhodeCode will simply add all new found repositories to 
   it's database. Also make sure You specify correct path to repositories.
 - Remember that the given path for mercurial_ repositories must be write 
   accessible for the application. It's very important since RhodeCode web interface
   will work even without such an access but, when trying to do a push it'll 
   eventually fail with permission denied errors. 
 - Run 
 
 ::
  
  paster serve production.ini
  
 - This command runs the rhodecode server the app should be available at the 
   127.0.0.1:5000. This ip and port is configurable via the production.ini 
   file  created in previous step
 - Use admin account you created to login.
 - Default permissions on each repository is read, and owner is admin. So 
   remember to update these if needed.
   
     
-Setting up Whoosh
------------------
+Setting up Whoosh full text search
+----------------------------------
+
+Index for whoosh can be build starting from version 1.1 using paster command
+passing repo locations to index, as well as Your config file that stores
+whoosh index files locations. There is possible to pass `-f` to the options
+to enable full index rebuild. Without that indexing will run always in in
+incremental mode.
+
+::
+ paster make-index --repo-location=<location for repos> production.ini  
+
+for full index rebuild You can use
+
+::
+ paster make-index -f --repo-location=<location for repos> production.ini
 
 - For full text search You can either put crontab entry for
 
+This command can be run even from crontab in order to do periodical 
+index builds and keep Your index always up to date. An example entry might 
+look like this
+
 ::
  
- python /var/www/rhodecode/<rhodecode_installation_path>/lib/indexers/daemon.py incremental <put_here_path_to_repos>
+ /path/to/python/bin/paster --repo-location=<location for repos> /path/to/rhodecode/production.ini
   
-When using incremental mode whoosh will check last modification date of each file
-and add it to reindex if newer file is available. Also indexing daemon checks
-for removed files and removes them from index. Sometime You might want to rebuild
-index from scrach, in admin pannel You can check `build from scratch` flag
-and in standalone daemon You can pass `full` instead on incremental to build
-remove previos index and build new one.
+When using incremental(default) mode whoosh will check last modification date 
+of each file and add it to reindex if newer file is available. Also indexing 
+daemon checks for removed files and removes them from index. 
+
+Sometime You might want to rebuild index from scratch. You can do that using 
+the `-f` flag passed to paster command or, in admin panel You can check 
+`build from scratch` flag.
 
 Nginx virtual host example
 --------------------------
 
 Sample config for nginx::
 
  server {
     listen          80;
     server_name     hg.myserver.com;
     access_log      /var/log/nginx/rhodecode.access.log;
     error_log       /var/log/nginx/rhodecode.error.log;
     location / {
             root /var/www/rhodecode/rhodecode/public/;
             if (!-f $request_filename){
                 proxy_pass      http://127.0.0.1:5000;
             }
             #this is important for https !!!
             proxy_set_header X-Url-Scheme $scheme;
             include         /etc/nginx/proxy.conf;  
     }
  }  
   
 Here's the proxy.conf. It's tuned so it'll not timeout on long
 pushes and also on large pushes::
 
     proxy_redirect              off;
     proxy_set_header            Host $host;
     proxy_set_header            X-Host $http_host;
     proxy_set_header            X-Real-IP $remote_addr;
     proxy_set_header            X-Forwarded-For $proxy_add_x_forwarded_for;
     proxy_set_header            Proxy-host $proxy_host;
     client_max_body_size        400m;
     client_body_buffer_size     128k;
     proxy_buffering             off;
     proxy_connect_timeout       3600;
     proxy_send_timeout          3600;
     proxy_read_timeout          3600;
     proxy_buffer_size           8k;
     proxy_buffers               8 32k;
     proxy_busy_buffers_size     64k;
     proxy_temp_file_write_size  64k;
  
 Also when using root path with nginx You might set the static files to false
 in production.ini file::
 
   [app:main]
     use = egg:rhodecode
     full_stack = true
     static_files = false
     lang=en
     cache_dir = %(here)s/data
 
 To not have the statics served by the application. And improve speed.
 
 
 Other configuration files
 -------------------------
 
 Some extra configuration files and examples can be found here:
 http://hg.python-works.com/rhodecode/files/tip/init.d
 
 and also an celeryconfig file can be use from here:
 http://hg.python-works.com/rhodecode/files/tip/celeryconfig.py
 
 
 
 .. _virtualenv: http://pypi.python.org/pypi/virtualenv
 .. _python: http://www.python.org/
 .. _mercurial: http://mercurial.selenic.com/
 .. _celery: http://celeryproject.org/
 .. _rabbitmq: http://www.rabbitmq.com/
  No newline at end of file

production.ini

@@ -1,174 +1,175 b''
 ################################################################################
 ################################################################################
 # rhodecode - Pylons environment configuration                                 #
 #                                                                              # 
 # The %(here)s variable will be replaced with the parent directory of this file#
 ################################################################################
 
 [DEFAULT]
 debug = true
 ################################################################################
 ## Uncomment and replace with the address which should receive                ## 
 ## any error reports after application crash                                  ##
 ## Additionally those settings will be used by rhodecode mailing system       ##
 ################################################################################
 #email_to = admin@localhost
 #error_email_from = paste_error@localhost
 #app_email_from = rhodecode-noreply@localhost
 #error_message =
 
 #smtp_server = mail.server.com
 #smtp_username = 
 #smtp_password = 
 #smtp_port = 
 #smtp_use_tls = false
 
 [server:main]
 ##nr of threads to spawn
 threadpool_workers = 5
 
 ##max request before thread respawn
 threadpool_max_requests = 2
 
 ##option to use threads of process
 use_threadpool = true
 
 use = egg:Paste#http
 host = 127.0.0.1
 port = 8001
 
 [app:main]
 use = egg:rhodecode
 full_stack = true
 static_files = false
 lang=en
 cache_dir = %(here)s/data
+index_dir = %(here)s/data/index
 
 ####################################
 ###         BEAKER CACHE        ####
 ####################################
 beaker.cache.data_dir=/%(here)s/data/cache/data
 beaker.cache.lock_dir=/%(here)s/data/cache/lock
 beaker.cache.regions=super_short_term,short_term,long_term,sql_cache_short,sql_cache_med,sql_cache_long
 
 beaker.cache.super_short_term.type=memory
 beaker.cache.super_short_term.expire=10
 
 beaker.cache.short_term.type=memory
 beaker.cache.short_term.expire=60
 
 beaker.cache.long_term.type=memory
 beaker.cache.long_term.expire=36000
 
 
 beaker.cache.sql_cache_short.type=memory
 beaker.cache.sql_cache_short.expire=5
 
 beaker.cache.sql_cache_med.type=memory
 beaker.cache.sql_cache_med.expire=360
 
 beaker.cache.sql_cache_long.type=file
 beaker.cache.sql_cache_long.expire=3600
 
 ####################################
 ###       BEAKER SESSION        ####
 ####################################
 ## Type of storage used for the session, current types are 
 ## dbm, file, memcached, database, and memory. 
 ## The storage uses the Container API 
 ##that is also used by the cache system.
 beaker.session.type = file
 
 beaker.session.key = rhodecode
 beaker.session.secret = g654dcno0-9873jhgfreyu
 beaker.session.timeout = 36000
 
 ##auto save the session to not to use .save()
 beaker.session.auto = False
 
 ##true exire at browser close
 #beaker.session.cookie_expires = 3600
 
     
 ################################################################################
 ## WARNING: *THE LINE BELOW MUST BE UNCOMMENTED ON A PRODUCTION ENVIRONMENT*  ##
 ## Debug mode will enable the interactive debugging tool, allowing ANYONE to  ##
 ## execute malicious code after an exception is raised.                       ##
 ################################################################################
 set debug = false
 
 ##################################
 ###       LOGVIEW CONFIG       ###
 ##################################
 logview.sqlalchemy = #faa
 logview.pylons.templating = #bfb
 logview.pylons.util = #eee
 
 #########################################################
 ### DB CONFIGS - EACH DB WILL HAVE IT'S OWN CONFIG    ###
 #########################################################
 sqlalchemy.db1.url = sqlite:///%(here)s/rhodecode.db
 #sqlalchemy.db1.echo = False
 #sqlalchemy.db1.pool_recycle = 3600
 sqlalchemy.convert_unicode = true
 
 ################################
 ### LOGGING CONFIGURATION   ####
 ################################
 [loggers]
 keys = root, routes, rhodecode, sqlalchemy
 
 [handlers]
 keys = console
 
 [formatters]
 keys = generic,color_formatter
 
 #############
 ## LOGGERS ##
 #############
 [logger_root]
 level = INFO
 handlers = console
 
 [logger_routes]
 level = INFO
 handlers = console
 qualname = routes.middleware
 # "level = DEBUG" logs the route matched and routing variables.
 propagate = 0
 
 [logger_rhodecode]
 level = DEBUG
 handlers = console
 qualname = rhodecode
 propagate = 0
 
 [logger_sqlalchemy]
 level = ERROR
 handlers = console
 qualname = sqlalchemy.engine
 propagate = 0
 
 ##############
 ## HANDLERS ##
 ##############
 
 [handler_console]
 class = StreamHandler
 args = (sys.stderr,)
 level = NOTSET
 formatter = color_formatter
 
 ################
 ## FORMATTERS ##
 ################
 
 [formatter_generic]
 format = %(asctime)s.%(msecs)03d %(levelname)-5.5s [%(name)s] %(message)s
 datefmt = %Y-%m-%d %H:%M:%S
 
 [formatter_color_formatter]
 class=rhodecode.lib.colored_formatter.ColorFormatter
 format= %(asctime)s.%(msecs)03d %(levelname)-5.5s [%(name)s] %(message)s
 datefmt = %Y-%m-%d %H:%M:%S
  No newline at end of file

rhodecode/config/deployment.ini_tmpl

@@ -1,174 +1,175 b''
 ################################################################################
 ################################################################################
 # rhodecode - Pylons environment configuration                                 #
 #                                                                              # 
 # The %(here)s variable will be replaced with the parent directory of this file#
 ################################################################################
 
 [DEFAULT]
 debug = true
 ################################################################################
 ## Uncomment and replace with the address which should receive                ## 
 ## any error reports after application crash                                  ##
 ## Additionally those settings will be used by rhodecode mailing system       ##
 ################################################################################
 #email_to = admin@localhost
 #error_email_from = paste_error@localhost
 #app_email_from = rhodecode-noreply@localhost
 #error_message =
 
 #smtp_server = mail.server.com
 #smtp_username = 
 #smtp_password = 
 #smtp_port = 
 #smtp_use_tls = false
 
 [server:main]
 ##nr of threads to spawn
 threadpool_workers = 5
 
 ##max request before thread respawn
 threadpool_max_requests = 10
 
 ##option to use threads of process
 use_threadpool = true
 
 use = egg:Paste#http
 host = 127.0.0.1
 port = 5000
 
 [app:main]
 use = egg:rhodecode
 full_stack = true
 static_files = true
 lang=en
 cache_dir = %(here)s/data
+index_dir = %(here)s/data/index
 app_instance_uuid = ${app_instance_uuid}
 
 ####################################
 ###         BEAKER CACHE        ####
 ####################################
 beaker.cache.data_dir=/%(here)s/data/cache/data
 beaker.cache.lock_dir=/%(here)s/data/cache/lock
 beaker.cache.regions=super_short_term,short_term,long_term,sql_cache_short,sql_cache_med,sql_cache_long
 
 beaker.cache.super_short_term.type=memory
 beaker.cache.super_short_term.expire=10
 
 beaker.cache.short_term.type=memory
 beaker.cache.short_term.expire=60
 
 beaker.cache.long_term.type=memory
 beaker.cache.long_term.expire=36000
 
 beaker.cache.sql_cache_short.type=memory
 beaker.cache.sql_cache_short.expire=5
 
 beaker.cache.sql_cache_med.type=memory
 beaker.cache.sql_cache_med.expire=360
 
 beaker.cache.sql_cache_long.type=file
 beaker.cache.sql_cache_long.expire=3600
 
 ####################################
 ###       BEAKER SESSION        ####
 ####################################
 ## Type of storage used for the session, current types are 
 ## dbm, file, memcached, database, and memory. 
 ## The storage uses the Container API 
 ##that is also used by the cache system.
 beaker.session.type = file
 
 beaker.session.key = rhodecode
 beaker.session.secret = ${app_instance_secret}
 beaker.session.timeout = 36000
 
 ##auto save the session to not to use .save()
 beaker.session.auto = False
 
 ##true exire at browser close
 #beaker.session.cookie_expires = 3600
 
     
 ################################################################################
 ## WARNING: *THE LINE BELOW MUST BE UNCOMMENTED ON A PRODUCTION ENVIRONMENT*  ##
 ## Debug mode will enable the interactive debugging tool, allowing ANYONE to  ##
 ## execute malicious code after an exception is raised.                       ##
 ################################################################################
 set debug = false
 
 ##################################
 ###       LOGVIEW CONFIG       ###
 ##################################
 logview.sqlalchemy = #faa
 logview.pylons.templating = #bfb
 logview.pylons.util = #eee
 
 #########################################################
 ### DB CONFIGS - EACH DB WILL HAVE IT'S OWN CONFIG    ###
 #########################################################
 sqlalchemy.db1.url = sqlite:///%(here)s/rhodecode.db
 #sqlalchemy.db1.echo = False
 #sqlalchemy.db1.pool_recycle = 3600
 sqlalchemy.convert_unicode = true
 
 ################################
 ### LOGGING CONFIGURATION   ####
 ################################
 [loggers]
 keys = root, routes, rhodecode, sqlalchemy
 
 [handlers]
 keys = console
 
 [formatters]
 keys = generic,color_formatter
 
 #############
 ## LOGGERS ##
 #############
 [logger_root]
 level = INFO
 handlers = console
 
 [logger_routes]
 level = INFO
 handlers = console
 qualname = routes.middleware
 # "level = DEBUG" logs the route matched and routing variables.
 propagate = 0
 
 [logger_rhodecode]
 level = DEBUG
 handlers = console
 qualname = rhodecode
 propagate = 0
 
 [logger_sqlalchemy]
 level = ERROR
 handlers = console
 qualname = sqlalchemy.engine
 propagate = 0
 
 ##############
 ## HANDLERS ##
 ##############
 
 [handler_console]
 class = StreamHandler
 args = (sys.stderr,)
 level = NOTSET
 formatter = color_formatter
 
 ################
 ## FORMATTERS ##
 ################
 
 [formatter_generic]
 format = %(asctime)s.%(msecs)03d %(levelname)-5.5s [%(name)s] %(message)s
 datefmt = %Y-%m-%d %H:%M:%S
 
 [formatter_color_formatter]
 class=rhodecode.lib.colored_formatter.ColorFormatter
 format= %(asctime)s.%(msecs)03d %(levelname)-5.5s [%(name)s] %(message)s
 datefmt = %Y-%m-%d %H:%M:%S
  No newline at end of file

rhodecode/lib/indexers/__init__.py

@@ -1,196 +1,192 b''
 import os
 import sys
 from os.path import dirname as dn, join as jn
 
 #to get the rhodecode import
 sys.path.append(dn(dn(dn(os.path.realpath(__file__)))))
 
 from rhodecode.config.environment import load_environment
 from rhodecode.model.hg import HgModel
 from shutil import rmtree
 from webhelpers.html.builder import escape
 from vcs.utils.lazy import LazyProperty
 
 from whoosh.analysis import RegexTokenizer, LowercaseFilter, StopFilter
 from whoosh.fields import TEXT, ID, STORED, Schema, FieldType
 from whoosh.index import create_in, open_dir
 from whoosh.formats import Characters
 from whoosh.highlight import highlight, SimpleFragmenter, HtmlFormatter
 
 import traceback
 
 
 #LOCATION WE KEEP THE INDEX
 IDX_LOCATION = jn(dn(dn(dn(dn(os.path.abspath(__file__))))), 'data', 'index')
 
 #EXTENSIONS WE WANT TO INDEX CONTENT OFF
 INDEX_EXTENSIONS = ['action', 'adp', 'ashx', 'asmx', 'aspx', 'asx', 'axd', 'c',
                     'cfg', 'cfm', 'cpp', 'cs', 'css', 'diff', 'do', 'el', 'erl',
                     'h', 'htm', 'html', 'ini', 'java', 'js', 'jsp', 'jspx', 'lisp',
                     'lua', 'm', 'mako', 'ml', 'pas', 'patch', 'php', 'php3',
                     'php4', 'phtml', 'pm', 'py', 'rb', 'rst', 's', 'sh', 'sql',
                     'tpl', 'txt', 'vim', 'wss', 'xhtml', 'xml', 'xsl', 'xslt',
                     'yaws']
 
 #CUSTOM ANALYZER wordsplit + lowercase filter
 ANALYZER = RegexTokenizer(expression=r"\w+") | LowercaseFilter()
 
 
 #INDEX SCHEMA DEFINITION
 SCHEMA = Schema(owner=TEXT(),
                 repository=TEXT(stored=True),
                 path=TEXT(stored=True),
                 content=FieldType(format=Characters(ANALYZER),
                              scorable=True, stored=True),
                 modtime=STORED(), extension=TEXT(stored=True))
 
 
 IDX_NAME = 'HG_INDEX'
 FORMATTER = HtmlFormatter('span', between='\n<span class="break">...</span>\n')
 FRAGMENTER = SimpleFragmenter(200)
 
 from paste.script import command
 import ConfigParser
 
 class MakeIndex(command.Command):
 
     max_args = 1
     min_args = 1
 
     usage = "CONFIG_FILE"
     summary = "Creates index for full text search given configuration file"
-    group_name = "Whoosh indexing"
-
+    group_name = "RhodeCode"
+    takes_config_file = -1
     parser = command.Command.standard_parser(verbose=True)
-#    parser.add_option('--repo-location',
-#                      action='store',
-#                      dest='repo_location',
-#                      help="Specifies repositories location to index",
-#                      )
+    parser.add_option('--repo-location',
+                      action='store',
+                      dest='repo_location',
+                      help="Specifies repositories location to index REQUIRED",
+                      )
     parser.add_option('-f',
                       action='store_true',
                       dest='full_index',
                       help="Specifies that index should be made full i.e"
                             " destroy old and build from scratch",
                       default=False)
     def command(self):
         config_name = self.args[0]
-
         p = config_name.split('/')
-        if len(p) == 1:
-            root = '.'
-        else:
-            root = '/'.join(p[:-1])
-        print root
+        root = '.' if len(p) == 1 else '/'.join(p[:-1])
         config = ConfigParser.ConfigParser({'here':root})
         config.read(config_name)
-        print dict(config.items('app:main'))['index_dir']
+
         index_location = dict(config.items('app:main'))['index_dir']
-        #return
+        repo_location = self.options.repo_location
 
-        #=======================================================================
+        #======================================================================
         # WHOOSH DAEMON
-        #=======================================================================
+        #======================================================================
         from rhodecode.lib.pidlock import LockHeld, DaemonLock
         from rhodecode.lib.indexers.daemon import WhooshIndexingDaemon
         try:
             l = DaemonLock()
-            WhooshIndexingDaemon(index_location=index_location)\
+            WhooshIndexingDaemon(index_location=index_location,
+                                 repo_location=repo_location)\
                 .run(full_index=self.options.full_index)
             l.release()
         except LockHeld:
             sys.exit(1)
 
 
 class ResultWrapper(object):
     def __init__(self, search_type, searcher, matcher, highlight_items):
         self.search_type = search_type
         self.searcher = searcher
         self.matcher = matcher
         self.highlight_items = highlight_items
         self.fragment_size = 200 / 2
 
     @LazyProperty
     def doc_ids(self):
         docs_id = []
         while self.matcher.is_active():
             docnum = self.matcher.id()
             chunks = [offsets for offsets in self.get_chunks()]
             docs_id.append([docnum, chunks])
             self.matcher.next()
         return docs_id
 
     def __str__(self):
         return '<%s at %s>' % (self.__class__.__name__, len(self.doc_ids))
 
     def __repr__(self):
         return self.__str__()
 
     def __len__(self):
         return len(self.doc_ids)
 
     def __iter__(self):
         """
         Allows Iteration over results,and lazy generate content
 
         *Requires* implementation of ``__getitem__`` method.
         """
         for docid in self.doc_ids:
             yield self.get_full_content(docid)
 
     def __getslice__(self, i, j):
         """
         Slicing of resultWrapper
         """
         slice = []
         for docid in self.doc_ids[i:j]:
             slice.append(self.get_full_content(docid))
         return slice
 
 
     def get_full_content(self, docid):
         res = self.searcher.stored_fields(docid[0])
         f_path = res['path'][res['path'].find(res['repository']) \
                              + len(res['repository']):].lstrip('/')
 
         content_short = self.get_short_content(res, docid[1])
         res.update({'content_short':content_short,
                     'content_short_hl':self.highlight(content_short),
                     'f_path':f_path})
 
         return res
 
     def get_short_content(self, res, chunks):
 
         return ''.join([res['content'][chunk[0]:chunk[1]] for chunk in chunks])
 
     def get_chunks(self):
         """
         Smart function that implements chunking the content
         but not overlap chunks so it doesn't highlight the same
         close occurrences twice.
         @param matcher:
         @param size:
         """
         memory = [(0, 0)]
         for span in self.matcher.spans():
             start = span.startchar or 0
             end = span.endchar or 0
             start_offseted = max(0, start - self.fragment_size)
             end_offseted = end + self.fragment_size
 
             if start_offseted < memory[-1][1]:
                 start_offseted = memory[-1][1]
             memory.append((start_offseted, end_offseted,))
             yield (start_offseted, end_offseted,)
 
     def highlight(self, content, top=5):
         if self.search_type != 'content':
             return ''
         hl = highlight(escape(content),
                  self.highlight_items,
                  analyzer=ANALYZER,
                  fragmenter=FRAGMENTER,
                  formatter=FORMATTER,
                  top=top)
         return hl

rhodecode/lib/indexers/daemon.py

@@ -1,217 +1,215 b''
 #!/usr/bin/env python
 # encoding: utf-8
 # whoosh indexer daemon for rhodecode
 # Copyright (C) 2009-2010 Marcin Kuzminski <[e-mail]>
 #
 # This program is free software; you can redistribute it and/or
 # modify it under the terms of the GNU General Public License
 # as published by the Free Software Foundation; version 2
 # of the License or (at your opinion) any later version of the license.
 # 
 # This program is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 # 
 # You should have received a copy of the GNU General Public License
 # along with this program; if not, write to the Free Software
 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
 # MA  02110-1301, USA.
 """
 Created on Jan 26, 2010
 
 @author: marcink
 A deamon will read from task table and run tasks
 """
 import sys
 import os
 from os.path import dirname as dn
 from os.path import join as jn
 
 #to get the rhodecode import
 project_path = dn(dn(dn(dn(os.path.realpath(__file__)))))
 sys.path.append(project_path)
 
 
 from rhodecode.model.hg import HgModel
 from rhodecode.lib.helpers import safe_unicode
 from whoosh.index import create_in, open_dir
 from shutil import rmtree
 from rhodecode.lib.indexers import INDEX_EXTENSIONS, SCHEMA, IDX_NAME
 
 from time import mktime
 from vcs.exceptions import ChangesetError, RepositoryError
 
 import logging
 
 log = logging.getLogger('whooshIndexer')
 # create logger
 log.setLevel(logging.DEBUG)
 log.propagate = False
 # create console handler and set level to debug
 ch = logging.StreamHandler()
 ch.setLevel(logging.DEBUG)
 
 # create formatter
 formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
 
 # add formatter to ch
 ch.setFormatter(formatter)
 
 # add ch to logger
 log.addHandler(ch)
 
 class WhooshIndexingDaemon(object):
     """
     Deamon for atomic jobs
     """
 
     def __init__(self, indexname='HG_INDEX', index_location=None,
                  repo_location=None):
         self.indexname = indexname
 
         self.index_location = index_location
         if not index_location:
             raise Exception('You have to provide index location')
 
         self.repo_location = repo_location
         if not repo_location:
             raise Exception('You have to provide repositories location')
 
-
-
-        self.repo_paths = HgModel.repo_scan('/', self.repo_location, None, True)
+        self.repo_paths = HgModel().repo_scan(self.repo_location, None, True)
         self.initial = False
         if not os.path.isdir(self.index_location):
             os.mkdir(self.index_location)
             log.info('Cannot run incremental index since it does not'
                      ' yet exist running full build')
             self.initial = True
 
     def get_paths(self, repo):
-        """
-        recursive walk in root dir and return a set of all path in that dir
+        """recursive walk in root dir and return a set of all path in that dir
         based on repository walk function
         """
         index_paths_ = set()
         try:
             for topnode, dirs, files in repo.walk('/', 'tip'):
                 for f in files:
                     index_paths_.add(jn(repo.path, f.path))
                 for dir in dirs:
                     for f in files:
                         index_paths_.add(jn(repo.path, f.path))
 
         except RepositoryError:
             pass
         return index_paths_
 
     def get_node(self, repo, path):
         n_path = path[len(repo.path) + 1:]
         node = repo.get_changeset().get_node(n_path)
         return node
 
     def get_node_mtime(self, node):
         return mktime(node.last_changeset.date.timetuple())
 
     def add_doc(self, writer, path, repo):
-        """Adding doc to writer"""
+        """Adding doc to writer this function itself fetches data from
+        the instance of vcs backend"""
         node = self.get_node(repo, path)
 
         #we just index the content of chosen files
         if node.extension in INDEX_EXTENSIONS:
             log.debug('    >> %s [WITH CONTENT]' % path)
             u_content = node.content
         else:
             log.debug('    >> %s' % path)
             #just index file name without it's content
             u_content = u''
 
         writer.add_document(owner=unicode(repo.contact),
                         repository=safe_unicode(repo.name),
                         path=safe_unicode(path),
                         content=u_content,
                         modtime=self.get_node_mtime(node),
                         extension=node.extension)
 
 
     def build_index(self):
         if os.path.exists(self.index_location):
             log.debug('removing previous index')
             rmtree(self.index_location)
 
         if not os.path.exists(self.index_location):
             os.mkdir(self.index_location)
 
         idx = create_in(self.index_location, SCHEMA, indexname=IDX_NAME)
         writer = idx.writer()
 
         for cnt, repo in enumerate(self.repo_paths.values()):
             log.debug('building index @ %s' % repo.path)
 
             for idx_path in self.get_paths(repo):
                 self.add_doc(writer, idx_path, repo)
 
         log.debug('>> COMMITING CHANGES <<')
         writer.commit(merge=True)
         log.debug('>>> FINISHED BUILDING INDEX <<<')
 
 
     def update_index(self):
         log.debug('STARTING INCREMENTAL INDEXING UPDATE')
 
         idx = open_dir(self.index_location, indexname=self.indexname)
         # The set of all paths in the index
         indexed_paths = set()
         # The set of all paths we need to re-index
         to_index = set()
 
         reader = idx.reader()
         writer = idx.writer()
 
         # Loop over the stored fields in the index
         for fields in reader.all_stored_fields():
             indexed_path = fields['path']
             indexed_paths.add(indexed_path)
 
             repo = self.repo_paths[fields['repository']]
 
             try:
                 node = self.get_node(repo, indexed_path)
             except ChangesetError:
                 # This file was deleted since it was indexed
                 log.debug('removing from index %s' % indexed_path)
                 writer.delete_by_term('path', indexed_path)
 
             else:
                 # Check if this file was changed since it was indexed
                 indexed_time = fields['modtime']
                 mtime = self.get_node_mtime(node)
                 if mtime > indexed_time:
                     # The file has changed, delete it and add it to the list of
                     # files to reindex
                     log.debug('adding to reindex list %s' % indexed_path)
                     writer.delete_by_term('path', indexed_path)
                     to_index.add(indexed_path)
 
         # Loop over the files in the filesystem
         # Assume we have a function that gathers the filenames of the
         # documents to be indexed
         for repo in self.repo_paths.values():
             for path in self.get_paths(repo):
                 if path in to_index or path not in indexed_paths:
                     # This is either a file that's changed, or a new file
                     # that wasn't indexed before. So index it!
                     self.add_doc(writer, path, repo)
                     log.debug('re indexing %s' % path)
 
         log.debug('>> COMMITING CHANGES <<')
         writer.commit(merge=True)
         log.debug('>>> FINISHED REBUILDING INDEX <<<')
 
     def run(self, full_index=False):
         """Run daemon"""
         if full_index or self.initial:
             self.build_index()
         else:
             self.update_index()

setup.cfg

@@ -1,42 +1,42 b''
 [egg_info]
-tag_build = rc4
+tag_build = beta
 tag_svn_revision = true
 
 [easy_install]
 find_links = http://www.pylonshq.com/download/
 
 [nosetests]
 verbose=True
 verbosity=2
 with-pylons=test.ini
 detailed-errors=1
 
 # Babel configuration
 [compile_catalog]
 domain = rhodecode
 directory = rhodecode/i18n
 statistics = true
 
 [extract_messages]
 add_comments = TRANSLATORS:
 output_file = rhodecode/i18n/rhodecode.pot
 width = 80
 
 [init_catalog]
 domain = rhodecode
 input_file = rhodecode/i18n/rhodecode.pot
 output_dir = rhodecode/i18n
 
 [update_catalog]
 domain = rhodecode
 input_file = rhodecode/i18n/rhodecode.pot
 output_dir = rhodecode/i18n
 previous = true
 
 [build_sphinx]
 source-dir = docs/
 build-dir  = docs/_build
 all_files  = 1
 
 [upload_sphinx]
 upload-dir = docs/_build/html
  No newline at end of file

setup.py

@@ -1,93 +1,98 b''
 from rhodecode import get_version
 import sys
 py_version = sys.version_info
 
 requirements = [
         "Pylons>=1.0.0",
         "SQLAlchemy>=0.6.5",
         "Mako>=0.3.5",
         "vcs>=0.1.10",
         "pygments>=1.3.0",
         "mercurial>=1.6.4",
         "whoosh>=1.3.1",
         "celery>=2.1.3",
         "py-bcrypt",
         "babel",
     ]
 
 classifiers = ['Development Status :: 4 - Beta',
                    'Environment :: Web Environment',
                    'Framework :: Pylons',
                    'Intended Audience :: Developers',
                    'License :: OSI Approved :: BSD License',
                    'Operating System :: OS Independent',
                    'Programming Language :: Python', ]
 
 if sys.version_info < (2, 6):
     requirements.append("simplejson")
     requirements.append("pysqlite")
 
 #additional files from project that goes somewhere in the filesystem
 #relative to sys.prefix
 data_files = []
 
 #additional files that goes into package itself
 package_data = {'rhodecode': ['i18n/*/LC_MESSAGES/*.mo', ], }
 
 description = ('Mercurial and Git repository browser/management with '
                'build in push/pull server and full text search')
 #long description
 try:
     readme_file = 'README.rst'
     changelog_file = 'docs/changelog.rst'
     long_description = open(readme_file).read() + '/n/n' + \
         open(changelog_file).read()
 
 except IOError, err:
     sys.stderr.write("[WARNING] Cannot find file specified as "
         "long_description (%s)\n or changelog (%s) skipping that file" \
             % (readme_file, changelog_file))
     long_description = description
 
 
 try:
     from setuptools import setup, find_packages
 except ImportError:
     from ez_setup import use_setuptools
     use_setuptools()
     from setuptools import setup, find_packages
 #packages
 packages = find_packages(exclude=['ez_setup'])
 
 setup(
     name='RhodeCode',
     version=get_version(),
     description=description,
     long_description=long_description,
     keywords='rhodiumcode mercurial web hgwebdir gitweb git replacement serving hgweb rhodecode',
     license='BSD',
     author='Marcin Kuzminski',
     author_email='[e-mail]',
     url='http://hg.python-works.com',
     install_requires=requirements,
     classifiers=classifiers,
     setup_requires=["PasteScript>=1.6.3"],
     data_files=data_files,
     packages=packages,
     include_package_data=True,
     test_suite='nose.collector',
     package_data=package_data,
     message_extractors={'rhodecode': [
             ('**.py', 'python', None),
             ('templates/**.mako', 'mako', {'input_encoding': 'utf-8'}),
             ('public/**', 'ignore', None)]},
     zip_safe=False,
     paster_plugins=['PasteScript', 'Pylons'],
     entry_points="""
     [paste.app_factory]
     main = rhodecode.config.middleware:make_app
 
     [paste.app_install]
     main = pylons.util:PylonsInstaller
+
+    [paste.global_paster_command]
+    make-index = rhodecode.lib.indexers:MakeIndex
+    upgrade-db = rhodecode.lib.utils:UpgradeDb
+        
     """,
 )