#
# style.prm - collection schema parameters
#
# This file is used to enable/disable index schema features through
# macro definitions similar to those allowed by the C preprocessor.
# This file is included in other style files using $include so
# that the selected features are propagated to the schemas of all
# tables in the index.  Refer to the style.prm discussion 
# in the chapter "Tuning Collections" in the Verity Collection Reference 
# for more information.

# -----------------------------------------------------------------
# The IDX-CONFIG parameter defines the storage format used to 
# encode the word positions in the index.  WCT (Word Count) format
# is a compact format, storing the ordinal counting position of the
# word from the beginning of the document.  PSW (Paragraph, Sentence,
# Word) format takes approximately 15-20% more disk space, but
# stores semantically accurate paragraph and sentence boundaries.
# Optionally, Many may be specified with either WCT or PSW to 
# improve the accuracy of the <MANY> operator at the expense of
# disk space and search performance.

# This example enables Word Count word position format (the default).
$define	IDX-CONFIG	"WCT"



#This example enable Word Count word position format but ignore
#sentence tagging. The word position is bumped upon sentence tokens.  
#However, the sentence breaks maybe incorrect, causing phrase op to fail
#to yield a hit. This option ignores sentence tagging during 
#the indexing time for word position counting(i.e. word positions will not 
#be bumped upon sentence breaks). 
#$define	IDX-CONFIG	"WCT NOEOS"


# This example turns on Paragraph/Sentence/Word word position format.
# It also enables the <MANY> operator accuracy improvement.
#$define IDX-CONFIG	"PSW Many"

# -----------------------------------------------------------------
# The IDXOPTS parameters define which index options are applied to
# the various index token tables.  The following index options are
# supported for each: Stemdex enables an index by the stem of each
# word. Casedex stores all case variants of a word separately, so
# one can search for case sensitive terms such as "Jobs", "Apple", 
# and "NeXT" more easily. Soundex stores phonetic representations
# of the word, using AT&T's standard soundex algorithm. Numdex 
# enables numeric search on attributes. Datedex enables date search
# on attributes.  Xdatedex does the same for xdates; Datedex and
# Xdatedex are mutually exclusive.  Dewey enables structured 
# search for zones.  The application may also store 1-4 bytes of 
# application-specific data with each word instance, in the form of 
# Location data and/or Qualify Instance data. These options are 
# specified separately for each token table: word, zone, 
# zone attribute and zone content.
$define	WORD-IDXOPTS	"Stemdex Casedex"
$define	ZONE-IDXOPTS	""
$define	ATTR-IDXOPTS	"Casedex"
#$define ZONE-CONTENT-IDXOPTS "Casedex"
#$define	NOUN-IDXOPTS	""
#$define	NPHR-IDXOPTS	""
$ifdef NOUN-IDXOPTS
  $ifdef NPHR-IDXOPTS
    $define NNP-IDXOPTS
  $endif
$endif

# The following example shows how to associate 4 bytes of Location
# and Qualify data with each word instance.
#$define	WORD-IDXOPTS	"Location4 Qualify4"

# The DEWEY-IDXOPTS setting below limits the maximum Dewey Ordered 
# path length to 128 levels.
$define	DEWEY-IDXOPTS	"MaxLevels 128"

# -----------------------------------------------------------------
# Clustering is enabled by uncommenting one of the DOC-FEATURES 
# lines below. DOC-FEATURES stores a feature vector for each 
# document in the Documents table. These features are used for 
# Clustering results and fast Query-by-Example.  See the discussions 
# on clustering in Verity Developer's Kit Programming Reference for 
# more information. 
# The maximum number of features can be controlled by appending 
# "MaxFtrs n" to the DOC-FEATURES string. The default is 25. 

# The example below creates the DOC-FEATURES from any of the words 
# in the document.
#$define DOC-FEATURES    "TF"

# The example below creates the DOC-FEATURES entirely from Nouns 
# and Noun Phrases.
$define DOC-FEATURES    "NNP"

# The example below creates the DOC-FEATURES entirely from Noun Phrases.
# $define DOC-FEATURES    "NP"

# -----------------------------------------------------------------
# Document Summarization is enabled by uncommenting one of
# the DOC-SUMMARIES lines below.  The summarization data is
# stored in the documents table so that it might easily be
# shown when displaying the results of a search.
# See the discussions on document summaries in the style.prm section 
# of the chapter "Tuning Collections" in the Verity Collection Reference
# for more information.

# The example below stores the best three sentences of
# the document, but not more than 500 bytes.
$define DOC-SUMMARIES   "XS MaxSents 3 MaxBytes 500 Zone"

# The example below stores the first four sentences of
# the document, but not more than 500 bytes.
#$define DOC-SUMMARIES   "LS MaxSents 4 MaxBytes 500"

# The example below stores the first 150 bytes of
# the document, with white space compressed.
#$define DOC-SUMMARIES   "LB MaxBytes 150"

#----------------------------------------------------------------
# Passage-based summarization is enabled by uncommenting the 
# DOC-PBSUMMARIES line below. This stores tokenized and 
# compressed text version of documents in the document table. 
# The tokenized texts can then be used in the passage-based  
# summarization, which delivers the summary with search term 
# highlighted.

# The example below stores up to 8K text for each document.
$define DOC-PBSUMMARIES "MaxBytes 8192"

# The example below to turn off the spanword instance vector cache during
# search time
#$define SPANWORD-CACHE	"InstVect"