##
## 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 = "ascii" # change if your corpus uses different charset
##:: language = "en" # insert ISO code for language (de, en, fr, ...)
#========================================================================#
##
## p-attributes (token annotations)
##
ATTRIBUTE word
ATTRIBUTE pos
ATTRIBUTE lemma
ATTRIBUTE no_data # to check error conditions if data files do not exist
##
## 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
ALIGNED vss