zebra.cfg.in

harvest是一个下载html网页得机器人

# Zebra configuration file

# location of zebra's schema and attribute files
#profilePath: .:/path1/to/tab:/path2/to/tab
profilePath: lib:@prefix@/lib/broker/tab

# files that describe the attribute sets supported
attset: bib1.att
#attset: gils.att

harvest.database:   harvest
harvest.recordId:   file
#harvest.recordType: grs.regx.soif
harvest.recordType: grs.sgml
harvest.storeKeys:  1

# uncomment if you want a copy of data
#harvest.storeData: 1

# this should speed up incremental indexing on large base with small
# changes
#isam: b

########################
# paths                #
########################
# make sure that you have enough space for index and index-shadow
# path/to/index1:100M path/to/index2:4G
# this means use 100MB in index1 directory and 4GB in index2
#
# index
#register: path/to/index1:size1 path/to/index2:size2 ...
register: zebra/index:4G

# shadow for safe update
#shadow: path/to/shadow1:size1 path/to/shadow2:size2 ...
shadow: zebra/index-shadow:4G

# where to keep lockfiles
lockDir: zebra/run

# temporary files used during zebraidx' update
keyTmpDir: zebra/tmp

# temporary result sets for server, defaults to /tmp
setTmpDir: zebra/tmp

# size of memory to use for the zebraidx in megabytes
memMax: 8