# PunkSearch settings file # You may want to change some properties, for example "org.punksearch.crawler.range" (see below) ################## # Common settings ################## # The index directory path resolving algorithm examines following cases (in order): # 1) path resolves exactly as specified if it starts from "/" (i.e. absolute path) # 2) path resolves to /index if the system property is specified # 3) path resolves to PUNKSEARCH_HOME/index if the environment variable is set # 4) path resolves to /index finally # # Do not forget to set PUNKSEARCH_HOME environment variable or "-Dorg.punksearch.home" system property or # "punksearch_home" context variable (either in web.xml or in any other way) for the web application # in case you do not use absolute path here. # # The index directory included in the zip file is just for quick start and contains some items to play with. # For example, try to search "linux" in the web GUI or use Luke to examine index contents. org.punksearch.index.dir=index # Timeout in msec used to check if smb/ftp host is online # Used both by crawler (find host to crawl) and by web interface (report online status) org.punksearch.online.timeout=1000 ################## # Crawler settings ################## # The range of IPs to (try to) crawl. # Use dash "-" to define continuous ranges, separate ranges by ",". # Range can be a single IP # # This property can also point to a file (either absolute path or relative to punksearch home). # In this case each line should define single IP range, lines starting with "#" are ignored. # The tail of any non-comment line (starts with first ",") is ignored, so you can supply a CSV file. org.punksearch.crawler.range=192.168.4.1-192.168.10.255,192.168.11.230 #org.punksearch.crawler.range=ip_list.csv # Deep of directory tree to crawl. # The files and directories deeper than the value will be skipped. org.punksearch.crawler.deep=7 # How many threads Crawler should use to index the network. # Experiments have shown what values > 10 result in errors during crawling. # This may be the result of routers have limit on ARP requests per second. # default: 5 org.punksearch.crawler.threads=5 # Days to keep items in index directory if source server is not accessible during crawling. # After this period items will be removed. # Set to "0" if you want the index to be rebuilt from scratch each time. # default: 7 org.punksearch.crawler.keepdays=7 # Should the crawler try to unlock the index directory if it is locked # Use with caution if you actively use both cron scheduled and web interface crawling # default: false org.punksearch.crawler.forceunlock=false # Following properties are used for FTP crawling and pretty self-explanatory org.punksearch.crawler.ftp.timeout=5000 org.punksearch.crawler.ftp.encoding.default=CP1251 org.punksearch.crawler.ftp.encoding.custom=192.168.5.100:UTF-8,192.168.6.204:KOI8-R org.punksearch.crawler.ftp.mode.default=passive org.punksearch.crawler.ftp.mode.custom= org.punksearch.crawler.ftp.user=anonymous org.punksearch.crawler.ftp.password=punksearch@code.google.com # Following properties are used for SMB crawling and pretty self-explanatory org.punksearch.crawler.smb.timeout=5000 org.punksearch.crawler.smb.domain= org.punksearch.crawler.smb.user= org.punksearch.crawler.smb.password= ################## # Search settings ################## # Whatever use leading "*" for user terms in queries. # If "false" user terms are surrounded by "*" on both sides: "*term*" # Otherwise only one "*" is appended at the end: "term*" # As you may assume already, the "false" value leads to more extensive search process => slow # Use "false" if you have fast CPU, small index or want to make extensive search org.punksearch.search.fast=true # Tabs to show in web interface. You must have corresponding file type for each tab. org.punksearch.web.tabs=films,serials,audio,clips,pictures