view release on metacpan or  search on metacpan

data/registry/vss  view on Meta::CPAN

##
## registry entry for corpus VSS
##

# long descriptive name for the corpus
NAME "Very Short Stories"
# corpus ID (must be lowercase in registry!)
ID   vss
# path to binary data files
HOME data/vss
# optional info file (displayed by "info;" command in CQP)
INFO data/vss/.info

# corpus properties provide additional information about the corpus:
##:: charset = "latin1"	# character encoding of corpus data
##:: language = "en"	# insert ISO code for language (de, en, fr, ...)
#========================================================================#


##
## p-attributes (token annotations)
##

ATTRIBUTE word
ATTRIBUTE pos
ATTRIBUTE lemma


##
## s-attributes (structural markup)
##

# <story num=".." title=".." author=".." year=".."> ... </story>
# (no recursive embedding allowed)
STRUCTURE story
STRUCTURE story_num	# [annotations]
STRUCTURE story_title	# [annotations]
STRUCTURE story_author	# [annotations]
STRUCTURE story_year	# [annotations]

# <chapter num=".."> ... </chapter>
# (no recursive embedding allowed)
STRUCTURE chapter
STRUCTURE chapter_num	# [annotations]

# <p> ... </p>
# (no recursive embedding allowed)
STRUCTURE p

# <s> ... </s>
# (no recursive embedding allowed)
STRUCTURE s