Implemented #647, option to pass list of default encoding used to encode to/decode from unicode

development.ini

@@ -1,422 +1,424 b''
 ################################################################################
 ################################################################################
 # RhodeCode - Pylons environment configuration                                 #
 #                                                                              # 
 # The %(here)s variable will be replaced with the parent directory of this file#
 ################################################################################
 
 [DEFAULT]
 debug = true
 pdebug = false
 ################################################################################
 ## 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 =
 #email_prefix = [RhodeCode]
 
 #smtp_server = mail.server.com
 #smtp_username = 
 #smtp_password = 
 #smtp_port = 
 #smtp_use_tls = false
 #smtp_use_ssl = true
 # Specify available auth parameters here (e.g. LOGIN PLAIN CRAM-MD5, etc.)
 #smtp_auth = 
 
 [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
 use = egg:waitress#main
 host = 0.0.0.0
 port = 5000
 
 [filter:proxy-prefix]
 # prefix middleware for rc
 use = egg:PasteDeploy#prefix
 prefix = /<your-prefix>
 
 [app:main]
 use = egg:rhodecode
 #filter-with = proxy-prefix
 full_stack = true
 static_files = true
 # Optional Languages
 # en, fr, ja, pt_BR, zh_CN, zh_TW
 lang = en
 cache_dir = %(here)s/data
 index_dir = %(here)s/data/index
 app_instance_uuid = rc-develop
 cut_off_limit = 256000
 force_https = false
 commit_parse_limit = 25
 use_gravatar = true
 
 ## alternative_gravatar_url allows you to use your own avatar server application
 ## the following parts of the URL will be replaced
 ## {email}        user email
 ## {md5email}     md5 hash of the user email (like at gravatar.com)
 ## {size}         size of the image that is expected from the server application
 ## {scheme}       http/https from RhodeCode server
 ## {netloc}       network location from RhodeCode server
 #alternative_gravatar_url = http://myavatarserver.com/getbyemail/{email}/{size}
 #alternative_gravatar_url = http://myavatarserver.com/getbymd5/{md5email}?s={size}
 
 container_auth_enabled = false
 proxypass_auth_enabled = false
+## default encoding used to convert from and to unicode
+## can be also a comma seperated list of encoding in case of mixed encodings
 default_encoding = utf8
 
 ## overwrite schema of clone url
 ## available vars:
 ## scheme - http/https
 ## user - current user
 ## pass - password 
 ## netloc - network location
 ## path - usually repo_name
 
 #clone_uri = {scheme}://{user}{pass}{netloc}{path}
 
 ## issue tracking mapping for commits messages
 ## comment out issue_pat, issue_server, issue_prefix to enable
 
 ## pattern to get the issues from commit messages
 ## default one used here is #<numbers> with a regex passive group for `#`
 ## {id} will be all groups matched from this pattern
 
 issue_pat = (?:\s*#)(\d+)
 
 ## server url to the issue, each {id} will be replaced with match
 ## fetched from the regex and {repo} is replaced with full repository name
 ## including groups {repo_name} is replaced with just name of repo
 
 issue_server_link = https://myissueserver.com/{repo}/issue/{id}
 
 ## prefix to add to link to indicate it's an url
 ## #314 will be replaced by <issue_prefix><id>
 
 issue_prefix = #
 
 ## issue_pat, issue_server_link, issue_prefix can have suffixes to specify
 ## multiple patterns, to other issues server, wiki or others
 ## below an example how to create a wiki pattern 
 #  #wiki-some-id -> https://mywiki.com/some-id
 
 #issue_pat_wiki = (?:wiki-)(.+)
 #issue_server_link_wiki = https://mywiki.com/{id}
 #issue_prefix_wiki = WIKI-
 
 
 ## instance-id prefix
 ## a prefix key for this instance used for cache invalidation when running 
 ## multiple instances of rhodecode, make sure it's globally unique for 
 ## all running rhodecode instances. Leave empty if you don't use it
 instance_id = 
 
 ## alternative return HTTP header for failed authentication. Default HTTP
 ## response is 401 HTTPUnauthorized. Currently HG clients have troubles with 
 ## handling that. Set this variable to 403 to return HTTPForbidden
 auth_ret_code =
 
 ####################################
 ###        CELERY CONFIG        ####
 ####################################
 use_celery = false
 broker.host = localhost
 broker.vhost = rabbitmqhost
 broker.port = 5672
 broker.user = rabbitmq
 broker.password = qweqwe
 
 celery.imports = rhodecode.lib.celerylib.tasks
 
 celery.result.backend = amqp
 celery.result.dburi = amqp://
 celery.result.serialier = json
 
 #celery.send.task.error.emails = true
 #celery.amqp.task.result.expires = 18000
 
 celeryd.concurrency = 2
 #celeryd.log.file = celeryd.log
 celeryd.log.level = debug
 celeryd.max.tasks.per.child = 1
 
 #tasks will never be sent to the queue, but executed locally instead.
 celery.always.eager = false
 
 ####################################
 ###         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.super_short_term.key_length = 256
 
 beaker.cache.short_term.type=memory
 beaker.cache.short_term.expire=60
 beaker.cache.short_term.key_length = 256
 
 beaker.cache.long_term.type=memory
 beaker.cache.long_term.expire=36000
 beaker.cache.long_term.key_length = 256
 
 beaker.cache.sql_cache_short.type=memory
 beaker.cache.sql_cache_short.expire=10
 beaker.cache.sql_cache_short.key_length = 256
 
 beaker.cache.sql_cache_med.type=memory
 beaker.cache.sql_cache_med.expire=360
 beaker.cache.sql_cache_med.key_length = 256
 
 beaker.cache.sql_cache_long.type=file
 beaker.cache.sql_cache_long.expire=3600
 beaker.cache.sql_cache_long.key_length = 256
 
 ####################################
 ###       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.
 
 ## db session ##
 #beaker.session.type = ext:database
 #beaker.session.sa.url = postgresql://postgres:qwe@localhost/rhodecode
 #beaker.session.table_name = db_session 
 
 ## encrypted cookie client side session, good for many instances ##
 #beaker.session.type = cookie
 
 ## file based cookies (default) ##
 #beaker.session.type = file
 
 
 beaker.session.key = rhodecode
 ## secure cookie requires AES python libraries ##
 #beaker.session.encrypt_key = g654dcno0-9873jhgfreyu
 #beaker.session.validate_key = 9712sds2212c--zxc123
 ## sets session as invalid if it haven't been accessed for given amount of time
 beaker.session.timeout = 2592000
 beaker.session.httponly = true
 #beaker.session.cookie_path = /<your-prefix>
 
 ## uncomment for https secure cookie ##
 beaker.session.secure = false
 
 ## auto save the session to not to use .save() ##
 beaker.session.auto = False
 
 ## default cookie expiration time in seconds `true` expire at browser close ##
 #beaker.session.cookie_expires = 3600
 
 
 ############################
 ## ERROR HANDLING SYSTEMS ##
 ############################
 
 ####################
 ### [errormator] ###
 ####################
 
 # Errormator is tailored to work with RhodeCode, see 
 # http://errormator.com for details how to obtain an account
 # you must install python package `errormator_client` to make it work
 
 # errormator enabled
 errormator = true
 
 errormator.server_url = https://api.errormator.com
 errormator.api_key = YOUR_API_KEY
 
 # TWEAK AMOUNT OF INFO SENT HERE
 
 # enables 404 error logging (default False)
 errormator.report_404 = false
 
 # time in seconds after request is considered being slow (default 1)
 errormator.slow_request_time = 1
 
 # record slow requests in application
 # (needs to be enabled for slow datastore recording and time tracking)
 errormator.slow_requests = true
 
 # enable hooking to application loggers
 # errormator.logging = true
 
 # minimum log level for log capture
 # errormator.logging.level = WARNING
 
 # send logs only from erroneous/slow requests
 # (saves API quota for intensive logging)
 errormator.logging_on_error = false
 
 # list of additonal keywords that should be grabbed from environ object 
 # can be string with comma separated list of words in lowercase
 # (by default client will always send following info:
 # 'REMOTE_USER', 'REMOTE_ADDR', 'SERVER_NAME', 'CONTENT_TYPE' + all keys that 
 # start with HTTP* this list be extended with additional keywords here
 errormator.environ_keys_whitelist = 
 
 
 # list of keywords that should be blanked from request object 
 # can be string with comma separated list of words in lowercase
 # (by default client will always blank keys that contain following words 
 # 'password', 'passwd', 'pwd', 'auth_tkt', 'secret', 'csrf'
 # this list be extended with additional keywords set here
 errormator.request_keys_blacklist =
 
 
 # list of namespaces that should be ignores when gathering log entries
 # can be string with comma separated list of namespaces
 # (by default the client ignores own entries: errormator_client.client)
 errormator.log_namespace_blacklist =  
 
 
 ################
 ### [sentry] ###
 ################
 
 # sentry is a alternative open source error aggregator
 # you must install python packages `sentry` and `raven` to enable 
 
 sentry.dsn = YOUR_DNS
 sentry.servers =
 sentry.name =
 sentry.key =
 sentry.public_key =
 sentry.secret_key =
 sentry.project =
 sentry.site =
 sentry.include_paths =
 sentry.exclude_paths =
 
 
 ################################################################################
 ## 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.url = postgresql://postgres:qwe@localhost/rhodecode
 sqlalchemy.db1.echo = false
 sqlalchemy.db1.pool_recycle = 3600
 sqlalchemy.db1.convert_unicode = true
 
 ################################
 ### LOGGING CONFIGURATION   ####
 ################################
 [loggers]
 keys = root, routes, rhodecode, sqlalchemy, beaker, templates, whoosh_indexer
 
 [handlers]
 keys = console, console_sql
 
 [formatters]
 keys = generic, color_formatter, color_formatter_sql
 
 #############
 ## LOGGERS ##
 #############
 [logger_root]
 level = NOTSET
 handlers = console
 
 [logger_routes]
 level = DEBUG
 handlers = 
 qualname = routes.middleware
 # "level = DEBUG" logs the route matched and routing variables.
 propagate = 1
 
 [logger_beaker]
 level = DEBUG
 handlers = 
 qualname = beaker.container
 propagate = 1
 
 [logger_templates]
 level = INFO
 handlers = 
 qualname = pylons.templating
 propagate = 1
 
 [logger_rhodecode]
 level = DEBUG
 handlers = 
 qualname = rhodecode
 propagate = 1
 
 [logger_sqlalchemy]
 level = INFO
 handlers = console_sql
 qualname = sqlalchemy.engine
 propagate = 0
 
 [logger_whoosh_indexer]
 level = DEBUG
 handlers = 
 qualname = whoosh_indexer
 propagate = 1
 
 ##############
 ## HANDLERS ##
 ##############
 
 [handler_console]
 class = StreamHandler
 args = (sys.stderr,)
 level = DEBUG
 formatter = color_formatter
 
 [handler_console_sql]
 class = StreamHandler
 args = (sys.stderr,)
 level = DEBUG
 formatter = color_formatter_sql
 
 ################
 ## 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
 
 [formatter_color_formatter_sql]
 class=rhodecode.lib.colored_formatter.ColorFormatterSql
 format= %(asctime)s.%(msecs)03d %(levelname)-5.5s [%(name)s] %(message)s
 datefmt = %Y-%m-%d %H:%M:%S

production.ini

@@ -1,422 +1,424 b''
 ################################################################################
 ################################################################################
 # RhodeCode - Pylons environment configuration                                 #
 #                                                                              # 
 # The %(here)s variable will be replaced with the parent directory of this file#
 ################################################################################
 
 [DEFAULT]
 debug = true
 pdebug = false
 ################################################################################
 ## 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 =
 #email_prefix = [RhodeCode]
 
 #smtp_server = mail.server.com
 #smtp_username = 
 #smtp_password = 
 #smtp_port = 
 #smtp_use_tls = false
 #smtp_use_ssl = true
 # Specify available auth parameters here (e.g. LOGIN PLAIN CRAM-MD5, etc.)
 #smtp_auth = 
 
 [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
 use = egg:waitress#main
 host = 127.0.0.1
 port = 8001
 
 [filter:proxy-prefix]
 # prefix middleware for rc
 use = egg:PasteDeploy#prefix
 prefix = /<your-prefix>
 
 [app:main]
 use = egg:rhodecode
 #filter-with = proxy-prefix
 full_stack = true
 static_files = true
 # Optional Languages
 # en, fr, ja, pt_BR, zh_CN, zh_TW
 lang = en
 cache_dir = %(here)s/data
 index_dir = %(here)s/data/index
 app_instance_uuid = rc-production
 cut_off_limit = 256000
 force_https = false
 commit_parse_limit = 50
 use_gravatar = true
 
 ## alternative_gravatar_url allows you to use your own avatar server application
 ## the following parts of the URL will be replaced
 ## {email}        user email
 ## {md5email}     md5 hash of the user email (like at gravatar.com)
 ## {size}         size of the image that is expected from the server application
 ## {scheme}       http/https from RhodeCode server
 ## {netloc}       network location from RhodeCode server
 #alternative_gravatar_url = http://myavatarserver.com/getbyemail/{email}/{size}
 #alternative_gravatar_url = http://myavatarserver.com/getbymd5/{md5email}?s={size}
 
 container_auth_enabled = false
 proxypass_auth_enabled = false
+## default encoding used to convert from and to unicode
+## can be also a comma seperated list of encoding in case of mixed encodings
 default_encoding = utf8
 
 ## overwrite schema of clone url
 ## available vars:
 ## scheme - http/https
 ## user - current user
 ## pass - password 
 ## netloc - network location
 ## path - usually repo_name
 
 #clone_uri = {scheme}://{user}{pass}{netloc}{path}
 
 ## issue tracking mapping for commits messages
 ## comment out issue_pat, issue_server, issue_prefix to enable
 
 ## pattern to get the issues from commit messages
 ## default one used here is #<numbers> with a regex passive group for `#`
 ## {id} will be all groups matched from this pattern
 
 issue_pat = (?:\s*#)(\d+)
 
 ## server url to the issue, each {id} will be replaced with match
 ## fetched from the regex and {repo} is replaced with full repository name
 ## including groups {repo_name} is replaced with just name of repo
 
 issue_server_link = https://myissueserver.com/{repo}/issue/{id}
 
 ## prefix to add to link to indicate it's an url
 ## #314 will be replaced by <issue_prefix><id>
 
 issue_prefix = #
 
 ## issue_pat, issue_server_link, issue_prefix can have suffixes to specify
 ## multiple patterns, to other issues server, wiki or others
 ## below an example how to create a wiki pattern 
 #  #wiki-some-id -> https://mywiki.com/some-id
 
 #issue_pat_wiki = (?:wiki-)(.+)
 #issue_server_link_wiki = https://mywiki.com/{id}
 #issue_prefix_wiki = WIKI-
 
 
 ## instance-id prefix
 ## a prefix key for this instance used for cache invalidation when running 
 ## multiple instances of rhodecode, make sure it's globally unique for 
 ## all running rhodecode instances. Leave empty if you don't use it
 instance_id = 
 
 ## alternative return HTTP header for failed authentication. Default HTTP
 ## response is 401 HTTPUnauthorized. Currently HG clients have troubles with 
 ## handling that. Set this variable to 403 to return HTTPForbidden
 auth_ret_code =
 
 ####################################
 ###        CELERY CONFIG        ####
 ####################################
 use_celery = false
 broker.host = localhost
 broker.vhost = rabbitmqhost
 broker.port = 5672
 broker.user = rabbitmq
 broker.password = qweqwe
 
 celery.imports = rhodecode.lib.celerylib.tasks
 
 celery.result.backend = amqp
 celery.result.dburi = amqp://
 celery.result.serialier = json
 
 #celery.send.task.error.emails = true
 #celery.amqp.task.result.expires = 18000
 
 celeryd.concurrency = 2
 #celeryd.log.file = celeryd.log
 celeryd.log.level = debug
 celeryd.max.tasks.per.child = 1
 
 #tasks will never be sent to the queue, but executed locally instead.
 celery.always.eager = false
 
 ####################################
 ###         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.super_short_term.key_length = 256
 
 beaker.cache.short_term.type=memory
 beaker.cache.short_term.expire=60
 beaker.cache.short_term.key_length = 256
 
 beaker.cache.long_term.type=memory
 beaker.cache.long_term.expire=36000
 beaker.cache.long_term.key_length = 256
 
 beaker.cache.sql_cache_short.type=memory
 beaker.cache.sql_cache_short.expire=10
 beaker.cache.sql_cache_short.key_length = 256
 
 beaker.cache.sql_cache_med.type=memory
 beaker.cache.sql_cache_med.expire=360
 beaker.cache.sql_cache_med.key_length = 256
 
 beaker.cache.sql_cache_long.type=file
 beaker.cache.sql_cache_long.expire=3600
 beaker.cache.sql_cache_long.key_length = 256
 
 ####################################
 ###       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.
 
 ## db session ##
 #beaker.session.type = ext:database
 #beaker.session.sa.url = postgresql://postgres:qwe@localhost/rhodecode
 #beaker.session.table_name = db_session 
 
 ## encrypted cookie client side session, good for many instances ##
 #beaker.session.type = cookie
 
 ## file based cookies (default) ##
 #beaker.session.type = file
 
 
 beaker.session.key = rhodecode
 ## secure cookie requires AES python libraries ##
 #beaker.session.encrypt_key = g654dcno0-9873jhgfreyu
 #beaker.session.validate_key = 9712sds2212c--zxc123
 ## sets session as invalid if it haven't been accessed for given amount of time
 beaker.session.timeout = 2592000
 beaker.session.httponly = true
 #beaker.session.cookie_path = /<your-prefix>
 
 ## uncomment for https secure cookie ##
 beaker.session.secure = false
 
 ## auto save the session to not to use .save() ##
 beaker.session.auto = False
 
 ## default cookie expiration time in seconds `true` expire at browser close ##
 #beaker.session.cookie_expires = 3600
 
 
 ############################
 ## ERROR HANDLING SYSTEMS ##
 ############################
 
 ####################
 ### [errormator] ###
 ####################
 
 # Errormator is tailored to work with RhodeCode, see 
 # http://errormator.com for details how to obtain an account
 # you must install python package `errormator_client` to make it work
 
 # errormator enabled
 errormator = true
 
 errormator.server_url = https://api.errormator.com
 errormator.api_key = YOUR_API_KEY
 
 # TWEAK AMOUNT OF INFO SENT HERE
 
 # enables 404 error logging (default False)
 errormator.report_404 = false
 
 # time in seconds after request is considered being slow (default 1)
 errormator.slow_request_time = 1
 
 # record slow requests in application
 # (needs to be enabled for slow datastore recording and time tracking)
 errormator.slow_requests = true
 
 # enable hooking to application loggers
 # errormator.logging = true
 
 # minimum log level for log capture
 # errormator.logging.level = WARNING
 
 # send logs only from erroneous/slow requests
 # (saves API quota for intensive logging)
 errormator.logging_on_error = false
 
 # list of additonal keywords that should be grabbed from environ object 
 # can be string with comma separated list of words in lowercase
 # (by default client will always send following info:
 # 'REMOTE_USER', 'REMOTE_ADDR', 'SERVER_NAME', 'CONTENT_TYPE' + all keys that 
 # start with HTTP* this list be extended with additional keywords here
 errormator.environ_keys_whitelist = 
 
 
 # list of keywords that should be blanked from request object 
 # can be string with comma separated list of words in lowercase
 # (by default client will always blank keys that contain following words 
 # 'password', 'passwd', 'pwd', 'auth_tkt', 'secret', 'csrf'
 # this list be extended with additional keywords set here
 errormator.request_keys_blacklist =
 
 
 # list of namespaces that should be ignores when gathering log entries
 # can be string with comma separated list of namespaces
 # (by default the client ignores own entries: errormator_client.client)
 errormator.log_namespace_blacklist =  
 
 
 ################
 ### [sentry] ###
 ################
 
 # sentry is a alternative open source error aggregator
 # you must install python packages `sentry` and `raven` to enable 
 
 sentry.dsn = YOUR_DNS
 sentry.servers =
 sentry.name =
 sentry.key =
 sentry.public_key =
 sentry.secret_key =
 sentry.project =
 sentry.site =
 sentry.include_paths =
 sentry.exclude_paths =
 
 
 ################################################################################
 ## 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.url = postgresql://postgres:qwe@localhost/rhodecode
 sqlalchemy.db1.echo = false
 sqlalchemy.db1.pool_recycle = 3600
 sqlalchemy.db1.convert_unicode = true
 
 ################################
 ### LOGGING CONFIGURATION   ####
 ################################
 [loggers]
 keys = root, routes, rhodecode, sqlalchemy, beaker, templates, whoosh_indexer
 
 [handlers]
 keys = console, console_sql
 
 [formatters]
 keys = generic, color_formatter, color_formatter_sql
 
 #############
 ## LOGGERS ##
 #############
 [logger_root]
 level = NOTSET
 handlers = console
 
 [logger_routes]
 level = DEBUG
 handlers = 
 qualname = routes.middleware
 # "level = DEBUG" logs the route matched and routing variables.
 propagate = 1
 
 [logger_beaker]
 level = DEBUG
 handlers = 
 qualname = beaker.container
 propagate = 1
 
 [logger_templates]
 level = INFO
 handlers = 
 qualname = pylons.templating
 propagate = 1
 
 [logger_rhodecode]
 level = DEBUG
 handlers = 
 qualname = rhodecode
 propagate = 1
 
 [logger_sqlalchemy]
 level = INFO
 handlers = console_sql
 qualname = sqlalchemy.engine
 propagate = 0
 
 [logger_whoosh_indexer]
 level = DEBUG
 handlers = 
 qualname = whoosh_indexer
 propagate = 1
 
 ##############
 ## HANDLERS ##
 ##############
 
 [handler_console]
 class = StreamHandler
 args = (sys.stderr,)
 level = INFO
 formatter = generic
 
 [handler_console_sql]
 class = StreamHandler
 args = (sys.stderr,)
 level = WARN
 formatter = generic
 
 ################
 ## 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
 
 [formatter_color_formatter_sql]
 class=rhodecode.lib.colored_formatter.ColorFormatterSql
 format= %(asctime)s.%(msecs)03d %(levelname)-5.5s [%(name)s] %(message)s
 datefmt = %Y-%m-%d %H:%M:%S

rhodecode/config/deployment.ini_tmpl

@@ -1,432 +1,434 b''
 ################################################################################
 ################################################################################
 # RhodeCode - Pylons environment configuration                                 #
 #                                                                              # 
 # The %(here)s variable will be replaced with the parent directory of this file#
 ################################################################################
 
 [DEFAULT]
 debug = true
 pdebug = false
 ################################################################################
 ## 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 =
 #email_prefix = [RhodeCode]
 
 #smtp_server = mail.server.com
 #smtp_username = 
 #smtp_password = 
 #smtp_port = 
 #smtp_use_tls = false
 #smtp_use_ssl = true
 # Specify available auth parameters here (e.g. LOGIN PLAIN CRAM-MD5, etc.)
 #smtp_auth = 
 
 [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
 use = egg:waitress#main
 host = 127.0.0.1
 port = 5000
 
 [filter:proxy-prefix]
 # prefix middleware for rc
 use = egg:PasteDeploy#prefix
 prefix = /<your-prefix>
 
 [app:main]
 use = egg:rhodecode
 #filter-with = proxy-prefix
 full_stack = true
 static_files = true
 # Optional Languages
 # en, fr, ja, pt_BR, zh_CN, zh_TW
 lang = en
 cache_dir = %(here)s/data
 index_dir = %(here)s/data/index
 app_instance_uuid = ${app_instance_uuid}
 cut_off_limit = 256000
 force_https = false
 commit_parse_limit = 50
 use_gravatar = true
 
 ## alternative_gravatar_url allows you to use your own avatar server application
 ## the following parts of the URL will be replaced
 ## {email}        user email
 ## {md5email}     md5 hash of the user email (like at gravatar.com)
 ## {size}         size of the image that is expected from the server application
 ## {scheme}       http/https from RhodeCode server
 ## {netloc}       network location from RhodeCode server
 #alternative_gravatar_url = http://myavatarserver.com/getbyemail/{email}/{size}
 #alternative_gravatar_url = http://myavatarserver.com/getbymd5/{md5email}?s={size}
 
 container_auth_enabled = false
 proxypass_auth_enabled = false
+## default encoding used to convert from and to unicode
+## can be also a comma seperated list of encoding in case of mixed encodings
 default_encoding = utf8
 
 ## overwrite schema of clone url
 ## available vars:
 ## scheme - http/https
 ## user - current user
 ## pass - password 
 ## netloc - network location
 ## path - usually repo_name
 
 #clone_uri = {scheme}://{user}{pass}{netloc}{path}
 
 ## issue tracking mapping for commits messages
 ## comment out issue_pat, issue_server, issue_prefix to enable
 
 ## pattern to get the issues from commit messages
 ## default one used here is #<numbers> with a regex passive group for `#`
 ## {id} will be all groups matched from this pattern
 
 issue_pat = (?:\s*#)(\d+)
 
 ## server url to the issue, each {id} will be replaced with match
 ## fetched from the regex and {repo} is replaced with full repository name
 ## including groups {repo_name} is replaced with just name of repo
 
 issue_server_link = https://myissueserver.com/{repo}/issue/{id}
 
 ## prefix to add to link to indicate it's an url
 ## #314 will be replaced by <issue_prefix><id>
 
 issue_prefix = #
 
 ## issue_pat, issue_server_link, issue_prefix can have suffixes to specify
 ## multiple patterns, to other issues server, wiki or others
 ## below an example how to create a wiki pattern 
 #  #wiki-some-id -> https://mywiki.com/some-id
 
 #issue_pat_wiki = (?:wiki-)(.+)
 #issue_server_link_wiki = https://mywiki.com/{id}
 #issue_prefix_wiki = WIKI-
 
 
 ## instance-id prefix
 ## a prefix key for this instance used for cache invalidation when running 
 ## multiple instances of rhodecode, make sure it's globally unique for 
 ## all running rhodecode instances. Leave empty if you don't use it
 instance_id = 
 
 ## alternative return HTTP header for failed authentication. Default HTTP
 ## response is 401 HTTPUnauthorized. Currently HG clients have troubles with 
 ## handling that. Set this variable to 403 to return HTTPForbidden
 auth_ret_code =
 
 ####################################
 ###        CELERY CONFIG        ####
 ####################################
 use_celery = false
 broker.host = localhost
 broker.vhost = rabbitmqhost
 broker.port = 5672
 broker.user = rabbitmq
 broker.password = qweqwe
 
 celery.imports = rhodecode.lib.celerylib.tasks
 
 celery.result.backend = amqp
 celery.result.dburi = amqp://
 celery.result.serialier = json
 
 #celery.send.task.error.emails = true
 #celery.amqp.task.result.expires = 18000
 
 celeryd.concurrency = 2
 #celeryd.log.file = celeryd.log
 celeryd.log.level = debug
 celeryd.max.tasks.per.child = 1
 
 #tasks will never be sent to the queue, but executed locally instead.
 celery.always.eager = false
 
 ####################################
 ###         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.super_short_term.key_length = 256
 
 beaker.cache.short_term.type=memory
 beaker.cache.short_term.expire=60
 beaker.cache.short_term.key_length = 256
 
 beaker.cache.long_term.type=memory
 beaker.cache.long_term.expire=36000
 beaker.cache.long_term.key_length = 256
 
 beaker.cache.sql_cache_short.type=memory
 beaker.cache.sql_cache_short.expire=10
 beaker.cache.sql_cache_short.key_length = 256
 
 beaker.cache.sql_cache_med.type=memory
 beaker.cache.sql_cache_med.expire=360
 beaker.cache.sql_cache_med.key_length = 256
 
 beaker.cache.sql_cache_long.type=file
 beaker.cache.sql_cache_long.expire=3600
 beaker.cache.sql_cache_long.key_length = 256
 
 ####################################
 ###       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.
 
 ## db session ##
 #beaker.session.type = ext:database
 #beaker.session.sa.url = postgresql://postgres:qwe@localhost/rhodecode
 #beaker.session.table_name = db_session 
 
 ## encrypted cookie client side session, good for many instances ##
 #beaker.session.type = cookie
 
 ## file based cookies (default) ##
 #beaker.session.type = file
 
 
 beaker.session.key = rhodecode
 ## secure cookie requires AES python libraries ##
 #beaker.session.encrypt_key = g654dcno0-9873jhgfreyu
 #beaker.session.validate_key = 9712sds2212c--zxc123
 ## sets session as invalid if it haven't been accessed for given amount of time
 beaker.session.timeout = 2592000
 beaker.session.httponly = true
 #beaker.session.cookie_path = /<your-prefix>
 
 ## uncomment for https secure cookie ##
 beaker.session.secure = false
 
 ## auto save the session to not to use .save() ##
 beaker.session.auto = False
 
 ## default cookie expiration time in seconds `true` expire at browser close ##
 #beaker.session.cookie_expires = 3600
 
 
 ############################
 ## ERROR HANDLING SYSTEMS ##
 ############################
 
 ####################
 ### [errormator] ###
 ####################
 
 # Errormator is tailored to work with RhodeCode, see 
 # http://errormator.com for details how to obtain an account
 # you must install python package `errormator_client` to make it work
 
 # errormator enabled
 errormator = true
 
 errormator.server_url = https://api.errormator.com
 errormator.api_key = YOUR_API_KEY
 
 # TWEAK AMOUNT OF INFO SENT HERE
 
 # enables 404 error logging (default False)
 errormator.report_404 = false
 
 # time in seconds after request is considered being slow (default 1)
 errormator.slow_request_time = 1
 
 # record slow requests in application
 # (needs to be enabled for slow datastore recording and time tracking)
 errormator.slow_requests = true
 
 # enable hooking to application loggers
 # errormator.logging = true
 
 # minimum log level for log capture
 # errormator.logging.level = WARNING
 
 # send logs only from erroneous/slow requests
 # (saves API quota for intensive logging)
 errormator.logging_on_error = false
 
 # list of additonal keywords that should be grabbed from environ object 
 # can be string with comma separated list of words in lowercase
 # (by default client will always send following info:
 # 'REMOTE_USER', 'REMOTE_ADDR', 'SERVER_NAME', 'CONTENT_TYPE' + all keys that 
 # start with HTTP* this list be extended with additional keywords here
 errormator.environ_keys_whitelist = 
 
 
 # list of keywords that should be blanked from request object 
 # can be string with comma separated list of words in lowercase
 # (by default client will always blank keys that contain following words 
 # 'password', 'passwd', 'pwd', 'auth_tkt', 'secret', 'csrf'
 # this list be extended with additional keywords set here
 errormator.request_keys_blacklist =
 
 
 # list of namespaces that should be ignores when gathering log entries
 # can be string with comma separated list of namespaces
 # (by default the client ignores own entries: errormator_client.client)
 errormator.log_namespace_blacklist =  
 
 
 ################
 ### [sentry] ###
 ################
 
 # sentry is a alternative open source error aggregator
 # you must install python packages `sentry` and `raven` to enable 
 
 sentry.dsn = YOUR_DNS
 sentry.servers =
 sentry.name =
 sentry.key =
 sentry.public_key =
 sentry.secret_key =
 sentry.project =
 sentry.site =
 sentry.include_paths =
 sentry.exclude_paths =
 
 
 ################################################################################
 ## 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    ###
 #########################################################
 
 # SQLITE [default]
 sqlalchemy.db1.url = sqlite:///%(here)s/rhodecode.db
  
 # POSTGRESQL
 # sqlalchemy.db1.url = postgresql://user:pass@localhost/rhodecode
 
 # MySQL
 # sqlalchemy.db1.url = mysql://user:pass@localhost/rhodecode
 
 # see sqlalchemy docs for others
 
 sqlalchemy.db1.echo = false
 sqlalchemy.db1.pool_recycle = 3600
 sqlalchemy.db1.convert_unicode = true
 
 ################################
 ### LOGGING CONFIGURATION   ####
 ################################
 [loggers]
 keys = root, routes, rhodecode, sqlalchemy, beaker, templates, whoosh_indexer
 
 [handlers]
 keys = console, console_sql
 
 [formatters]
 keys = generic, color_formatter, color_formatter_sql
 
 #############
 ## LOGGERS ##
 #############
 [logger_root]
 level = NOTSET
 handlers = console
 
 [logger_routes]
 level = DEBUG
 handlers = 
 qualname = routes.middleware
 # "level = DEBUG" logs the route matched and routing variables.
 propagate = 1
 
 [logger_beaker]
 level = DEBUG
 handlers = 
 qualname = beaker.container
 propagate = 1
 
 [logger_templates]
 level = INFO
 handlers = 
 qualname = pylons.templating
 propagate = 1
 
 [logger_rhodecode]
 level = DEBUG
 handlers = 
 qualname = rhodecode
 propagate = 1
 
 [logger_sqlalchemy]
 level = INFO
 handlers = console_sql
 qualname = sqlalchemy.engine
 propagate = 0
 
 [logger_whoosh_indexer]
 level = DEBUG
 handlers = 
 qualname = whoosh_indexer
 propagate = 1
 
 ##############
 ## HANDLERS ##
 ##############
 
 [handler_console]
 class = StreamHandler
 args = (sys.stderr,)
 level = INFO
 formatter = generic
 
 [handler_console_sql]
 class = StreamHandler
 args = (sys.stderr,)
 level = WARN
 formatter = generic
 
 ################
 ## 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
 
 [formatter_color_formatter_sql]
 class=rhodecode.lib.colored_formatter.ColorFormatterSql
 format= %(asctime)s.%(msecs)03d %(levelname)-5.5s [%(name)s] %(message)s
 datefmt = %Y-%m-%d %H:%M:%S

rhodecode/lib/utils2.py

@@ -1,525 +1,557 b''
 # -*- coding: utf-8 -*-
 """
     rhodecode.lib.utils
     ~~~~~~~~~~~~~~~~~~~
 
     Some simple helper functions
 
     :created_on: Jan 5, 2011
     :author: marcink
     :copyright: (C) 2011-2012 Marcin Kuzminski <[e-mail]>
     :license: GPLv3, see COPYING for more details.
 """
 # 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, either version 3 of the License, or
 # (at your option) any later version.
 #
 # 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, see <http://www.gnu.org/licenses/>.
 
 import re
 import time
 import datetime
 import webob
 
 from pylons.i18n.translation import _, ungettext
 from rhodecode.lib.vcs.utils.lazy import LazyProperty
 
 
 def __get_lem():
     """
     Get language extension map based on what's inside pygments lexers
     """
     from pygments import lexers
     from string import lower
     from collections import defaultdict
 
     d = defaultdict(lambda: [])
 
     def __clean(s):
         s = s.lstrip('*')
         s = s.lstrip('.')
 
         if s.find('[') != -1:
             exts = []
             start, stop = s.find('['), s.find(']')
 
             for suffix in s[start + 1:stop]:
                 exts.append(s[:s.find('[')] + suffix)
             return map(lower, exts)
         else:
             return map(lower, [s])
 
     for lx, t in sorted(lexers.LEXERS.items()):
         m = map(__clean, t[-2])
         if m:
             m = reduce(lambda x, y: x + y, m)
             for ext in m:
                 desc = lx.replace('Lexer', '')
                 d[ext].append(desc)
 
     return dict(d)
 
+
 def str2bool(_str):
     """
     returs True/False value from given string, it tries to translate the
     string into boolean
 
     :param _str: string value to translate into boolean
     :rtype: boolean
     :returns: boolean from given string
     """
     if _str is None:
         return False
     if _str in (True, False):
         return _str
     _str = str(_str).strip().lower()
     return _str in ('t', 'true', 'y', 'yes', 'on', '1')
 
 
+def aslist(obj, sep=None, strip=True):
+    """
+    Returns given string separated by sep as list
+
+    :param obj:
+    :param sep:
+    :param strip:
+    """
+    if isinstance(obj, (basestring)):
+        lst = obj.split(sep)
+        if strip:
+            lst = [v.strip() for v in lst]
+        return lst
+    elif isinstance(obj, (list, tuple)):
+        return obj
+    elif obj is None:
+        return []
+    else:
+        return [obj]
+
+
 def convert_line_endings(line, mode):
     """
     Converts a given line  "line end" accordingly to given mode
 
     Available modes are::
         0 - Unix
         1 - Mac
         2 - DOS
 
     :param line: given line to convert
     :param mode: mode to convert to
     :rtype: str
     :return: converted line according to mode
     """
     from string import replace
 
     if mode == 0:
             line = replace(line, '\r\n', '\n')
             line = replace(line, '\r', '\n')
     elif mode == 1:
             line = replace(line, '\r\n', '\r')
             line = replace(line, '\n', '\r')
     elif mode == 2:
             line = re.sub("\r(?!\n)|(?<!\r)\n", "\r\n", line)
     return line
 
 
 def detect_mode(line, default):
     """
     Detects line break for given line, if line break couldn't be found
     given default value is returned
 
     :param line: str line
     :param default: default
     :rtype: int
     :return: value of line end on of 0 - Unix, 1 - Mac, 2 - DOS
     """
     if line.endswith('\r\n'):
         return 2
     elif line.endswith('\n'):
         return 0
     elif line.endswith('\r'):
         return 1
     else:
         return default
 
 
 def generate_api_key(username, salt=None):
     """
     Generates unique API key for given username, if salt is not given
     it'll be generated from some random string
 
     :param username: username as string
     :param salt: salt to hash generate KEY
     :rtype: str
     :returns: sha1 hash from username+salt
     """
     from tempfile import _RandomNameSequence
     import hashlib
 
     if salt is None:
         salt = _RandomNameSequence().next()
 
     return hashlib.sha1(username + salt).hexdigest()
 
 
 def safe_int(val, default=None):
     """
     Returns int() of val if val is not convertable to int use default
     instead
 
     :param val:
     :param default:
     """
 
     try:
         val = int(val)
     except ValueError:
         val = default
 
     return val
 
 
 def safe_unicode(str_, from_encoding=None):
     """
     safe unicode function. Does few trick to turn str_ into unicode
 
     In case of UnicodeDecode error we try to return it with encoding detected
     by chardet library if it fails fallback to unicode with errors replaced
 
     :param str_: string to decode
     :rtype: unicode
     :returns: unicode object
     """
     if isinstance(str_, unicode):
         return str_
 
     if not from_encoding:
         import rhodecode
-        DEFAULT_ENCODING = rhodecode.CONFIG.get('default_encoding','utf8')
-        from_encoding = DEFAULT_ENCODING
+        DEFAULT_ENCODINGS = aslist(rhodecode.CONFIG.get('default_encoding',
+                                                        'utf8'), sep=',')
+        from_encoding = DEFAULT_ENCODINGS
+
+    if not isinstance(from_encoding, (list, tuple)):
+        from_encoding = [from_encoding]
 
     try:
         return unicode(str_)
     except UnicodeDecodeError:
         pass
 
-    try:
-        return unicode(str_, from_encoding)
-    except UnicodeDecodeError:
-        pass
+    for enc in from_encoding:
+        try:
+            return unicode(str_, enc)
+        except UnicodeDecodeError:
+            pass
 
     try:
         import chardet
         encoding = chardet.detect(str_)['encoding']
         if encoding is None:
             raise Exception()
         return str_.decode(encoding)
     except (ImportError, UnicodeDecodeError, Exception):
-        return unicode(str_, from_encoding, 'replace')
+        return unicode(str_, from_encoding[0], 'replace')
 
 
 def safe_str(unicode_, to_encoding=None):
     """
     safe str function. Does few trick to turn unicode_ into string
 
     In case of UnicodeEncodeError we try to return it with encoding detected
     by chardet library if it fails fallback to string with errors replaced
 
     :param unicode_: unicode to encode
     :rtype: str
     :returns: str object
     """
 
     # if it's not basestr cast to str
     if not isinstance(unicode_, basestring):
         return str(unicode_)
 
     if isinstance(unicode_, str):
         return unicode_
 
     if not to_encoding:
         import rhodecode
-        DEFAULT_ENCODING = rhodecode.CONFIG.get('default_encoding','utf8')
-        to_encoding = DEFAULT_ENCODING
+        DEFAULT_ENCODINGS = aslist(rhodecode.CONFIG.get('default_encoding',
+                                                        'utf8'), sep=',')
+        to_encoding = DEFAULT_ENCODINGS
 
-    try:
-        return unicode_.encode(to_encoding)
-    except UnicodeEncodeError:
-        pass
+    if not isinstance(to_encoding, (list, tuple)):
+        to_encoding = [to_encoding]
+
+    for enc in to_encoding:
+        try:
+            return unicode_.encode(enc)
+        except UnicodeEncodeError:
+            pass
 
     try:
         import chardet
         encoding = chardet.detect(unicode_)['encoding']
         if encoding is None:
             raise UnicodeEncodeError()
 
         return unicode_.encode(encoding)
     except (ImportError, UnicodeEncodeError):
-        return unicode_.encode(to_encoding, 'replace')
+        return unicode_.encode(to_encoding[0], 'replace')
 
     return safe_str
 
 
 def engine_from_config(configuration, prefix='sqlalchemy.', **kwargs):
     """
     Custom engine_from_config functions that makes sure we use NullPool for
     file based sqlite databases. This prevents errors on sqlite. This only
     applies to sqlalchemy versions < 0.7.0
 
     """
     import sqlalchemy
     from sqlalchemy import engine_from_config as efc
     import logging
 
     if int(sqlalchemy.__version__.split('.')[1]) < 7:
 
         # This solution should work for sqlalchemy < 0.7.0, and should use
         # proxy=TimerProxy() for execution time profiling
 
         from sqlalchemy.pool import NullPool
         url = configuration[prefix + 'url']
 
         if url.startswith('sqlite'):
             kwargs.update({'poolclass': NullPool})
         return efc(configuration, prefix, **kwargs)
     else:
         import time
         from sqlalchemy import event
         from sqlalchemy.engine import Engine
 
         log = logging.getLogger('sqlalchemy.engine')
         BLACK, RED, GREEN, YELLOW, BLUE, MAGENTA, CYAN, WHITE = xrange(30, 38)
         engine = efc(configuration, prefix, **kwargs)
 
         def color_sql(sql):
             COLOR_SEQ = "\033[1;%dm"
             COLOR_SQL = YELLOW
             normal = '\x1b[0m'
             return ''.join([COLOR_SEQ % COLOR_SQL, sql, normal])
 
         if configuration['debug']:
             #attach events only for debug configuration
 
             def before_cursor_execute(conn, cursor, statement,
                                     parameters, context, executemany):
                 context._query_start_time = time.time()
                 log.info(color_sql(">>>>> STARTING QUERY >>>>>"))
 
             def after_cursor_execute(conn, cursor, statement,
                                     parameters, context, executemany):
                 total = time.time() - context._query_start_time
                 log.info(color_sql("<<<<< TOTAL TIME: %f <<<<<" % total))
 
             event.listen(engine, "before_cursor_execute",
                          before_cursor_execute)
             event.listen(engine, "after_cursor_execute",
                          after_cursor_execute)
 
     return engine
 
 
 def age(prevdate):
     """
     turns a datetime into an age string.
 
     :param prevdate: datetime object
     :rtype: unicode
     :returns: unicode words describing age
     """
 
     order = ['year', 'month', 'day', 'hour', 'minute', 'second']
     deltas = {}
     future = False
 
     # Get date parts deltas
     now = datetime.datetime.now()
     if prevdate > now:
         now, prevdate = prevdate, now
         future = True
 
     for part in order:
         deltas[part] = getattr(now, part) - getattr(prevdate, part)
 
     # Fix negative offsets (there is 1 second between 10:59:59 and 11:00:00,
     # not 1 hour, -59 minutes and -59 seconds)
 
     for num, length in [(5, 60), (4, 60), (3, 24)]:  # seconds, minutes, hours
         part = order[num]
         carry_part = order[num - 1]
 
         if deltas[part] < 0:
             deltas[part] += length
             deltas[carry_part] -= 1
 
     # Same thing for days except that the increment depends on the (variable)
     # number of days in the month
     month_lengths = [31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31]
     if deltas['day'] < 0:
         if prevdate.month == 2 and (prevdate.year % 4 == 0 and
             (prevdate.year % 100 != 0 or prevdate.year % 400 == 0)):
             deltas['day'] += 29
         else:
             deltas['day'] += month_lengths[prevdate.month - 1]
 
         deltas['month'] -= 1
 
     if deltas['month'] < 0:
         deltas['month'] += 12
         deltas['year'] -= 1
 
     # Format the result
     fmt_funcs = {
         'year': lambda d: ungettext(u'%d year', '%d years', d) % d,
         'month': lambda d: ungettext(u'%d month', '%d months', d) % d,
         'day': lambda d: ungettext(u'%d day', '%d days', d) % d,
         'hour': lambda d: ungettext(u'%d hour', '%d hours', d) % d,
         'minute': lambda d: ungettext(u'%d minute', '%d minutes', d) % d,
         'second': lambda d: ungettext(u'%d second', '%d seconds', d) % d,
     }
 
     for i, part in enumerate(order):
         value = deltas[part]
         if value == 0:
             continue
 
         if i < 5:
             sub_part = order[i + 1]
             sub_value = deltas[sub_part]
         else:
             sub_value = 0
 
         if sub_value == 0:
             if future:
                 return _(u'in %s') % fmt_funcs[part](value)
             else:
                 return _(u'%s ago') % fmt_funcs[part](value)
         if future:
             return _(u'in %s and %s') % (fmt_funcs[part](value),
                 fmt_funcs[sub_part](sub_value))
         else:
             return _(u'%s and %s ago') % (fmt_funcs[part](value),
                 fmt_funcs[sub_part](sub_value))
 
     return _(u'just now')
 
 
 def uri_filter(uri):
     """
     Removes user:password from given url string
 
     :param uri:
     :rtype: unicode
     :returns: filtered list of strings
     """
     if not uri:
         return ''
 
     proto = ''
 
     for pat in ('https://', 'http://'):
         if uri.startswith(pat):
             uri = uri[len(pat):]
             proto = pat
             break
 
     # remove passwords and username
     uri = uri[uri.find('@') + 1:]
 
     # get the port
     cred_pos = uri.find(':')
     if cred_pos == -1:
         host, port = uri, None
     else:
         host, port = uri[:cred_pos], uri[cred_pos + 1:]
 
     return filter(None, [proto, host, port])
 
 
 def credentials_filter(uri):
     """
     Returns a url with removed credentials
 
     :param uri:
     """
 
     uri = uri_filter(uri)
     #check if we have port
     if len(uri) > 2 and uri[2]:
         uri[2] = ':' + uri[2]
 
     return ''.join(uri)
 
 
 def get_changeset_safe(repo, rev):
     """
     Safe version of get_changeset if this changeset doesn't exists for a
     repo it returns a Dummy one instead
 
     :param repo:
     :param rev:
     """
     from rhodecode.lib.vcs.backends.base import BaseRepository
     from rhodecode.lib.vcs.exceptions import RepositoryError
     from rhodecode.lib.vcs.backends.base import EmptyChangeset
     if not isinstance(repo, BaseRepository):
         raise Exception('You must pass an Repository '
                         'object as first argument got %s', type(repo))
 
     try:
         cs = repo.get_changeset(rev)
     except RepositoryError:
         cs = EmptyChangeset(requested_revision=rev)
     return cs
 
 
 def datetime_to_time(dt):
     if dt:
         return time.mktime(dt.timetuple())
 
 
 def time_to_datetime(tm):
     if tm:
         if isinstance(tm, basestring):
             try:
                 tm = float(tm)
             except ValueError:
                 return
         return datetime.datetime.fromtimestamp(tm)
 
 MENTIONS_REGEX = r'(?:^@|\s@)([a-zA-Z0-9]{1}[a-zA-Z0-9\-\_\.]+)(?:\s{1})'
 
 
 def extract_mentioned_users(s):
     """
     Returns unique usernames from given string s that have @mention
 
     :param s: string to get mentions
     """
     usrs = set()
     for username in re.findall(MENTIONS_REGEX, s):
         usrs.add(username)
 
     return sorted(list(usrs), key=lambda k: k.lower())
 
 
 class AttributeDict(dict):
     def __getattr__(self, attr):
         return self.get(attr, None)
     __setattr__ = dict.__setitem__
     __delattr__ = dict.__delitem__
 
 
 def fix_PATH(os_=None):
     """
     Get current active python path, and append it to PATH variable to fix issues
     of subprocess calls and different python versions
     """
     import sys
     if os_ is None:
         import os
     else:
         os = os_
 
     cur_path = os.path.split(sys.executable)[0]
     if not os.environ['PATH'].startswith(cur_path):
         os.environ['PATH'] = '%s:%s' % (cur_path, os.environ['PATH'])
 
 
 def obfuscate_url_pw(engine):
     from sqlalchemy.engine import url
     url = url.make_url(engine)
     if url.password:
         url.password = 'XXXXX'
     return str(url)
 
 
 def get_server_url(environ):
     req = webob.Request(environ)
     return req.host_url + req.script_name

rhodecode/lib/vcs/utils/__init__.py

@@ -1,138 +1,137 b''
 """
 This module provides some useful tools for ``vcs`` like annotate/diff html
 output. It also includes some internal helpers.
 """
 import sys
 import time
 import datetime
 
 
 def makedate():
     lt = time.localtime()
     if lt[8] == 1 and time.daylight:
         tz = time.altzone
     else:
         tz = time.timezone
     return time.mktime(lt), tz
 
 
 def date_fromtimestamp(unixts, tzoffset=0):
     """
     Makes a local datetime object out of unix timestamp
 
     :param unixts:
     :param tzoffset:
     """
 
     return datetime.datetime.fromtimestamp(float(unixts))
 
 
 def safe_unicode(str_, from_encoding=None):
     """
     safe unicode function. Does few trick to turn str_ into unicode
 
     In case of UnicodeDecode error we try to return it with encoding detected
     by chardet library if it fails fallback to unicode with errors replaced
 
     :param str_: string to decode
     :rtype: unicode
     :returns: unicode object
     """
+    from rhodecode.lib.utils2 import safe_unicode
+    return safe_unicode(str_, from_encoding)
+
     if isinstance(str_, unicode):
         return str_
-    if not from_encoding:
-        import rhodecode
-        DEFAULT_ENCODING = rhodecode.CONFIG.get('default_encoding', 'utf8')
-        from_encoding = DEFAULT_ENCODING
+
     try:
         return unicode(str_)
     except UnicodeDecodeError:
         pass
 
     try:
         return unicode(str_, from_encoding)
     except UnicodeDecodeError:
         pass
 
     try:
         import chardet
         encoding = chardet.detect(str_)['encoding']
         if encoding is None:
             raise Exception()
         return str_.decode(encoding)
     except (ImportError, UnicodeDecodeError, Exception):
         return unicode(str_, from_encoding, 'replace')
 
 
 def safe_str(unicode_, to_encoding=None):
     """
     safe str function. Does few trick to turn unicode_ into string
 
     In case of UnicodeEncodeError we try to return it with encoding detected
     by chardet library if it fails fallback to string with errors replaced
 
     :param unicode_: unicode to encode
     :rtype: str
     :returns: str object
     """
+    from rhodecode.lib.utils2 import safe_str
+    return safe_str(unicode_, to_encoding)
 
     if isinstance(unicode_, str):
         return unicode_
-    if not to_encoding:
-        import rhodecode
-        DEFAULT_ENCODING = rhodecode.CONFIG.get('default_encoding', 'utf8')
-        to_encoding = DEFAULT_ENCODING
+
     try:
         return unicode_.encode(to_encoding)
     except UnicodeEncodeError:
         pass
 
     try:
         import chardet
         encoding = chardet.detect(unicode_)['encoding']
         if encoding is None:
             raise UnicodeEncodeError()
 
         return unicode_.encode(encoding)
     except (ImportError, UnicodeEncodeError):
         return unicode_.encode(to_encoding, 'replace')
 
     return safe_str
 
 
 def author_email(author):
     """
     returns email address of given author.
     If any of <,> sign are found, it fallbacks to regex findall()
     and returns first found result or empty string
 
     Regex taken from http://www.regular-expressions.info/email.html
     """
     import re
     r = author.find('>')
     l = author.find('<')
 
     if l == -1 or r == -1:
         # fallback to regex match of email out of a string
         email_re = re.compile(r"""[a-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[a-z0-9!"""
                               r"""#$%&'*+/=?^_`{|}~-]+)*@(?:[a-z0-9](?:[a-z"""
                               r"""0-9-]*[a-z0-9])?\.)+[a-z0-9](?:[a-z0-9-]"""
                               r"""*[a-z0-9])?""", re.IGNORECASE)
         m = re.findall(email_re, author)
         return m[0] if m else ''
 
     return author[l + 1:r].strip()
 
 
 def author_name(author):
     """
     get name of author, or else username.
     It'll try to find an email in the author string and just cut it off
     to get the username
     """
 
     if not '@' in author:
         return author
     else:
         return author.replace(author_email(author), '').replace('<', '')\
             .replace('>', '').strip()