index_threads = 10
maxmemdocs = 2000000
index_divisor = 1
shards = 1000
use_journal = 1
index_path = /home/tabolin/lucene-test-index
#index_path = /u0/mdb301/
primary_key = url

xurls_regex_file = ../../rpm/lucene-xurls-patterns/src/lucene_xurls_patterns

[access_log]
file = /home/tabolin/log/lucene/access.log
rotate = number
date.locale = en

[index_log]
file = /home/tabolin/log/lucene/index.log
rotate = number
separator = \ 
date.format = dd/MMM/yyyy:HH:mm:ss
date.locale = en
level.show = false

[index_access_log]
file = /home/tabolin/log/lucene/index-access.log
rotate = number
date.locale = en

[error_log]
file = /home/tabolin/log/lucene/error.log
rotate = number
separator = \ 
date.format = dd/MMM/yyyy:HH:mm:ss
date.locale = en
level.show = false

[full_log]
file = /home/tabolin/log/lucene/full.log
rotate = number
level.min = all

# plain old http server config
[http]
port = 1089
timeout = 10000
# ignored
connections = 100
workers.min = 200

# new search server config
[search]
port = 8089
timeout = 10000
connections = 1000
workers.min = 100

# json indexer config
[indexer]
port = 8182
timeout = 100000
connections = 1000
workers.min = 200

# Yandex codec config
[yandex_codec]
terms_writer_block_size = 8192
fields_writer_buffer_size = 6144

[field.url]
tokenizer = keyword
store = true
attribute = true

[field.mimetype]
tokenizer = keyword
filters = lowercase
prefixed = true
store = true
analyze = true
attribute = true
index_alias = mimetype_np

[field.mimetype_np]
tokenizer = keyword
filters = lowercase
analyze = true
attribute = true

[field.disposition_type]
tokenizer = keyword
filters = lowercase
prefixed = true
store = true
analyze = true
attribute = true

[field.hdr_from]
tokenizer = letter
filters = lowercase|replace:ё:е
prefixed = true
store = true
analyze = true
index_alias = hdr_from_keyword

[field.hdr_from_keyword]
tokenizer = keyword
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.hdr_from_email]
tokenizer = lf
filters = lowercase
prefixed = true
analyze = true
attribute = true

[field.hdr_from_display_name]
tokenizer = lf
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.hdr_from_normalized]
tokenizer = lf
filters = lowercase
prefixed = true
store = true
analyze = true
attribute = true

[field.reply_to]
tokenizer = letter
filters = lowercase|replace:ё:е
prefixed = true
store = true
analyze = true
index_alias = reply_to_keyword

[field.reply_to_keyword]
tokenizer = keyword
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.reply_to_email]
tokenizer = lf
filters = lowercase
prefixed = true
analyze = true
attribute = true

[field.reply_to_display_name]
tokenizer = lf
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.reply_to_normalized]
tokenizer = lf
filters = lowercase
prefixed = true
store = true
analyze = true
attribute = true

[field.hdr_to]
tokenizer = letter
filters = lowercase|replace:ё:е
prefixed = true
store = true
analyze = true
index_alias = hdr_to_keyword

[field.hdr_to_keyword]
tokenizer = keyword
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.hdr_to_email]
tokenizer = lf
filters = lowercase
prefixed = true
analyze = true
attribute = true

[field.hdr_to_display_name]
tokenizer = lf
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.hdr_to_normalized]
tokenizer = lf
filters = lowercase
prefixed = true
store = true
analyze = true
attribute = true

[field.hdr_cc]
tokenizer = letter
filters = lowercase|replace:ё:е
prefixed = true
store = true
analyze = true
index_alias = hdr_cc_keyword

[field.hdr_cc_keyword]
tokenizer = keyword
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.hdr_cc_email]
tokenizer = lf
filters = lowercase
prefixed = true
analyze = true
attribute = true

[field.hdr_cc_display_name]
tokenizer = lf
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.hdr_cc_normalized]
tokenizer = lf
filters = lowercase
prefixed = true
store = true
analyze = true
attribute = true

[field.hdr_bcc]
tokenizer = letter
filters = lowercase|replace:ё:е
prefixed = true
store = true
analyze = true
index_alias = hdr_bcc_keyword

[field.hdr_bcc_keyword]
tokenizer = keyword
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.hdr_bcc_email]
tokenizer = lf
filters = lowercase
prefixed = true
analyze = true
attribute = true

[field.hdr_bcc_display_name]
tokenizer = lf
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.hdr_bcc_normalized]
tokenizer = lf
filters = lowercase
prefixed = true
store = true
analyze = true
attribute = true

[field.hdr_subject]
tokenizer = letter
filters = truncate:64|lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true
index_alias = hdr_subject_keyword

[field.hdr_subject_keyword]
tokenizer = keyword
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.hdr_subject_normalized]
tokenizer = letter
filters = truncate:64|lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true
index_alias = hdr_subject_normalized_keyword

[field.hdr_subject_normalized_keyword]
tokenizer = keyword
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.msg_id]
tokenizer = keyword
prefixed = true
store = true
analyze = true
attribute = true

[field.body_text]
tokenizer = letter
filters = truncate:64|lowercase|replace:ё:е|lemmer
prefixed = true
analyze = true

[field.pure_body]
tokenizer = letter
filters = truncate:64|lowercase|replace:ё:е|lemmer
prefixed = true
analyze = true

[field.ocr_text]
tokenizer = letter
filters = truncate:64|lowercase|replace:ё:е|lemmer
store = true
prefixed = true
analyze = true

[field.received_date]
tokenizer = keyword
filters = padding:10
prefixed = true
store = true
analyze = true
attribute = true
type = integer
index_alias = received_day

[field.received_day]
tokenizer = keyword
filters = daf:86400|padding:10
analyze = true
attribute = true
index_alias = received_day_p

[field.received_day_p]
tokenizer = keyword
filters = daf:86400|padding:10
prefixed = true
analyze = true
attribute = true

[field.mid]
store = true
type = long
index_alias = mid_p

[field.mid_p]
tokenizer = keyword
prefixed = true
analyze = true
attribute = true
index_alias = mid_padded

[field.mid_padded]
tokenizer = keyword
filters = padding:20
prefixed = true
analyze = true
attribute = true

[field.hid]
tokenizer = keyword
prefixed = true
store = true
analyze = true
attribute = true

[field.fid]
prefixed = true
store = true
analyze = true
attribute = true

[field.stid]
store = true
analyze = true
attribute = true

[field.thread_id]
prefixed = true
store = true
analyze = true
attribute = true

[field.suid]
tokenizer = keyword
store = true
attribute = true

[field.uid]
tokenizer = keyword
store = true
attribute = true

[field.headers]
tokenizer = lf
filters = lowercase|headers
prefixed = true
analyze = true
attribute = true

[field.attachsize]
tokenizer = keyword
filters = padding:10
prefixed = true
store = true
analyze = true
attribute = true

[field.attachsize_b]
tokenizer = keyword
filters = padding:20
prefixed = true
store = true
analyze = true
attribute = true

[field.attachsize_kb]
tokenizer = keyword
filters = padding:20
prefixed = true
store = true
analyze = true
attribute = true

[field.attachname]
tokenizer = letter
filters = lowercase|replace:ё:е
prefixed = true
store = true
analyze = true
index_alias = attachname_keyword
# TODO: remove this field after Yandex.Mail reindex
search_alias = attachname_backward_compatibility

[field.attachname_backward_compatibility]
tokenizer = letter
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true
search_alias = attachname_keyword

[field.attachname_keyword]
tokenizer = keyword
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.attachtype]
tokenizer = letter
filters = lowercase|replace:ё:е
prefixed = true
store = true
analyze = true
attribute = true

[field.attachments]
tokenizer = letter
filters = lowercase|replace:ё:е
prefixed = true
store = true
analyze = true
index_alias = attachments_keyword

[field.attachments_keyword]
tokenizer = lf
filters = lowercase|replace:ё:е
prefixed = true
analyze = true
attribute = true

[field.md5]
tokenizer = keyword
store = true
analyze = true
attribute = true
index_alias = md5_p

[field.md5_p]
tokenizer = keyword
prefixed = true
analyze = true
attribute = true

[field.x_urls]
tokenizer = boolean
prefixed = true
store = true
analyze = true
attribute = true

[field.message_type]
tokenizer = letter
prefixed = true
store = true
analyze = true
attribute = true

[field.built_date]
tokenizer = keyword
store = true
analyze = true
attribute = true

[field.parsed]
tokenizer = keyword
analyze = true
attribute = true

[field.meta]
tokenizer = lf
filters = lowercase|headers
prefixed = true
analyze = true
attribute = true

[field.error]
tokenizer = boolean
store = true
analyze = true
attribute = true

[field.truncated]
tokenizer = keyword
filters = padding:10
store = true
prefixed = true
analyze = true
attribute = true
type = integer

[field.has_attachments]
tokenizer = boolean
prefixed = true
analyze = true
attribute = true

[field.draft]
tokenizer = boolean
prefixed = true
analyze = true
attribute = true

[field.lcn]
tokenizer = keyword
filters = padding:20
store = true
prefixed = true
analyze = true
attribute = true
type = long

[field.album]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.album_tracks]
tokenizer = keyword
filters = padding:3
prefixed = true
store = true
analyze = true
attribute = true
type = integer

[field.altitude]
tokenizer = keyword
filters = maf:1000000|padding:10
prefixed = true
store = true
analyze = true
attribute = true
type = float

[field.artist]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.author]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.comment]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.composer]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.created]
tokenizer = keyword
filters = padding:10
prefixed = true
store = true
analyze = true
attribute = true
type = integer

[field.description]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.duration]
tokenizer = keyword
filters = maf:100|padding:10
prefixed = true
store = true
analyze = true
attribute = true
type = float

[field.genre]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.height]
tokenizer = keyword
filters = padding:10
prefixed = true
store = true
analyze = true
attribute = true
type = integer

[field.keywords]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.latitude]
tokenizer = keyword
filters = aaz:90|maf:1000000|padding:10
prefixed = true
store = true
analyze = true
attribute = true
type = float

[field.longitude]
tokenizer = keyword
filters = aaz:180|maf:1000000|padding:10
prefixed = true
store = true
analyze = true
attribute = true
type = float

[field.manufacturer]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.model]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.modified]
tokenizer = keyword
filters = padding:10
prefixed = true
store = true
analyze = true
attribute = true
type = integer

[field.orientation]
tokenizer = keyword
prefixed = true
store = true
analyze = true
attribute = true

[field.pages]
tokenizer = keyword
filters = padding:5
prefixed = true
store = true
analyze = true
attribute = true
type = integer

[field.print_date]
tokenizer = keyword
filters = padding:10
prefixed = true
store = true
analyze = true
attribute = true
type = integer

[field.producer]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.ratio]
tokenizer = keyword
prefixed = true
store = true
analyze = true
attribute = true

[field.released]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.subject]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.title]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.tool]
tokenizer = letter
filters = lowercase|replace:ё:е|lemmer
prefixed = true
store = true
analyze = true

[field.track_number]
tokenizer = keyword
filters = padding:3
prefixed = true
store = true
analyze = true
attribute = true
type = integer

[field.width]
tokenizer = keyword
filters = padding:10
prefixed = true
store = true
analyze = true
attribute = true
type = integer

[field.abook_suid]
tokenizer = keyword
store = true
attribute = true

[field.abook_name]
tokenizer = lf
filters = lowercase|replace:ё:е
prefixed = true
store = true
analyze = true
attribute = true

[field.abook_email]
tokenizer = letter
filters = lowercase|replace:ё:е
prefixed = true
store = true
analyze = true
index_alias = abook_email_exact

[field.abook_email_exact]
tokenizer = lf
filters = lowercase
prefixed = true
analyze = true

[field.abook_phone]
tokenizer = letter
filters = lowercase
prefixed = true
store = true
analyze = true

[field.abook_source_type]
tokenizer = lf
filters = lowercase
prefixed = true
store = true
analyze = true

[field.abook_id]
tokenizer = keyword
filters = lowercase
prefixed = true
store = true
analyze = true

[field.abook_revision]
tokenizer = keyword
filters = lowercase
prefixed = true
store = true
analyze = true

[field.abook_last_contacted]
tokenizer = keyword
filters = padding:10
prefixed = true
store = true
analyze = true
attribute = true
type = integer

[field.abook_times_contacted]
tokenizer = keyword
filters = lowercase
prefixed = true
store = true
analyze = true

[field.abook_photo_base]
tokenizer = letter
filters = lowercase|replace:ё:е
prefixed = true
store = true
analyze = true

[field.blackbox_lastauth]
type = integer
store = true
index = false

[field.senders_suid]
tokenizer = keyword
store = true
attribute = true

[field.senders_last_contacted]
tokenizer = keyword
filters = padding:10
prefixed = true
store = true
analyze = true
attribute = true
type = integer

[field.senders_received_count]
tokenizer = keyword
prefixed = true
store = true
analyze = true
type = integer

[field.senders_sent_count]
tokenizer = keyword
prefixed = true
store = true
analyze = true
type = integer

[field.senders_names]
tokenizer = lf
filters = lowercase|replace:ё:е
prefixed = true
store = true
analyze = true
attribute = true

[field.senders_lcn]
tokenizer = keyword
filters = padding:20
store = true
prefixed = true
analyze = true
attribute = true
type = long

[field.kv_service]
tokenizer = keyword
prefixed = true
store = true
analyze = true
attribute = true
index_alias = kv_service_np

[field.kv_service_np]
tokenizer = keyword
attribute = true

[field.kv_suid]
tokenizer = keyword
store = true
attribute = true

[field.kv_data]
store = true
index = false

[field.kv_number]
type = long
store = true
index = false

