view release on metacpan or  search on metacpan

etc/alvis-nlpplatform/nlpplatform.rc  view on Meta::CPAN

# definition of the linguistic annotation steps

ALVISTMP	= $HOME/tmp

PLATFORM_ROOT	= $HOME/Platform

AWK		= /usr/bin/awk

DEBUG           = 0

<alvis_connection>
	HARVESTER_PORT	= 6234
	NEXTSTEP	= 0
	NEXTSTEP_HOST	= localhost
	NEXTSTEP_PORT	= 7345
	SPOOLDIR	= $HOME/tmp/spool
	OUTDIR		= $HOME/tmp/Outdir
</alvis_connection>

<NLP_connection>
	SERVER			= localhost
	PORT			= 1510
	RETRY_CONNECTION	= 10
</NLP_connection>

<XML_INPUT>
    PRESERVEWHITESPACE = 0
    LINGUISTIC_ANNOTATION_LOADING = 0
</XML_INPUT>


<XML_OUTPUT>
    FORM = 1
    ID = 1
    TOKEN_LEVEL = 1
    SEMANTIC_UNIT_NAMED_ENTITY_LEVEL	= 1
    WORD_LEVEL	= 1
    SENTENCE_LEVEL = 1
    MORPHOSYNTACTIC_FEATURE_LEVEL	= 1
    LEMMA_LEVEL	= 1
    SEMANTIC_UNIT_TERM_LEVEL	= 1
    SEMANTIC_UNIT_LEVEL	= 1
    SYNTACTIC_RELATION_LEVEL	= 1

    NO_STD_XML_OUTPUT = 0

    YATEA = 1
</XML_OUTPUT>

<linguistic_annotation>
	ENABLE_TOKEN	= 1
	ENABLE_NER	= 1
	ENABLE_WORD	= 1
	ENABLE_SENTENCE = 1
	ENABLE_POS	= 1
	ENABLE_LEMMA	= 1
	ENABLE_TERM_TAG	= 1
	ENABLE_SYNTAX	= 0
	ENABLE_SEMANTIC_TAG	= 0
</linguistic_annotation>

<NLP_misc>
	NLP_resources	= $PLATFORM_ROOT/Resources
	SAVE_IN_OUTDIR	= 1
	TERM_LIST_EN	= $NLP_resources/terms.txt.sav
	TERM_LIST_FR	= $NLP_resources/terms_FR.txt
    # valid tags for each language
    <POSTAG_LIST>
        <EN>
	    CC = 1
	    CD = 1
    	    DT = 1
            EX = 1
            FW = 1
            IN = 1
            JJ = 1
            JJR = 1
            JJS = 1
            LS = 1
            MD = 1
            NN = 1
            NNS = 1
            NP = 1
            NPS = 1
            PDT = 1
            POS = 1
            PP = 1
            PP$ = 1
            RB = 1
            RBR = 1
            RBS = 1
            RP = 1
            SYM = 1
            TO = 1
            UH = 1
            VB = 1
            VBD = 1
            VBG = 1
            VBN = 1
            VBP = 1
            VBZ = 1
            VV = 1
            VVD = 1
            VVG = 1
            VVN = 1
            VVP = 1
            VVZ = 1
            WDT = 1

etc/alvis-nlpplatform/nlpplatform.rc  view on Meta::CPAN

            PRO = 1
            PRO:DEM = 1
            PRO:IND = 1
            PRO:PER = 1
            PRO:POS = 1
            PRO:REL = 1
            PRP = 1
            PRP:det = 1
            PUN = 2
            PUN:cit = 2
            SENT = 2
            SYM = 1
            VER:cond = 1
            VER:futu = 1
            VER:impe = 1
            VER:impf = 1
            VER:infi = 1
            VER:pper = 1
            VER:ppre = 1
            VER:pres = 1
            VER:simp = 1
            VER:subi = 1
            VER:subp = 1
        </FR>
        
    </POSTAG_LIST>
</NLP_misc>

NLP_tools_root = $PLATFORM_ROOT/NLPtools

SEMTAG_EN_DIR = $NLP_tools_root/AlvisSemTag-0.4
ONTOLOGY = $SEMTAG_EN_DIR/share/Subtilis_Molecular_Biology-v2.rdf
CANONICAL_DICT = $SEMTAG_EN_DIR/share/canonical_head_variants.dict.trish2 # optional
PARENT_DICT = $SEMTAG_EN_DIR/share/Subtilis_Molecular_Biology-v2.parent.trish2 # optional

<NLP_tools>
	NETAG_EN		= "$NLP_tools_root/TagEN/tagen -t -y :bio"
	NETAG_FR		= "$NLP_tools_root/TagEN/tagen -t -y :equer"
	WORDSEG_EN		= "$AWK -f $NLP_tools_root/WordSeg/words-en.awk"
	# WORDSEG_EN		= "$NLP_tools_root/WordSeg/sentences.pl"
	WORDSEG_FR		= "$AWK -f $NLP_tools_root/WordSeg/words-fr.awk"
	POSTAG_EN		= "$NLP_tools_root/TreeTagger/bin/tree-tagger $NLP_tools_root/TreeTagger/lib/english.par -token -lemma -sgml -no-unknown"
	#POSTAG_EN		= "(cd $NLP_tools_root/geniatagger-2.0.1; sed 's/ /___/g' | tr '\n' ' '| ./geniatagger -nt | cut -f 1,2,3|sed 's/\([^\t]*\t\)\([^\t]*\)\t\([^\t]*\)/\1\3\t\2/g' | sed 's/___/ /g' | grep -v '^$')"
	POSTAG_FR		= "$NLP_tools_root/TreeTagger/bin/tree-tagger $NLP_tools_root/TreeTagger/lib/french.par -token -lemma -sgml -no-unknown"
	SYNTACTIC_PATH_EN	= "$NLP_tools_root/link-4.1b"
	# SYNTACTIC_PATH_EN       = "$NLP_tools_root/biolgForAlvis/biolg-1.1.7b"
	SYNTACTIC_PATH_FR	= ""
	SYNTACTIC_ANALYSIS_EN	= "cd $SYNTACTIC_PATH_EN ; $SYNTACTIC_PATH_EN/parse"

# 	SYNTACTIC_PATH_EN_SUPPL       = "/home/thierry/Recherche/Logiciels/LP2LP"
#         SYNTACTIC_ANALYSIS_EN_LP2LP_CLEAN       = "cd $SYNTACTIC_PATH_EN_SUPPL ; $SYNTACTIC_PATH_EN_SUPPL/clean_BioLG_output_for_lp2lp.pl"
#         SYNTACTIC_ANALYSIS_EN_LP2LP     = "cd $SYNTACTIC_PATH_EN_SUPPL ; $SYNTACTIC_PATH_EN_SUPPL/lp2lp/lp2lp -r $SYNTACTIC_PATH_EN_SUPPL/lp2lp/test/lp2lp.conf"

	# SYNTACTIC_ANALYSIS_EN	= "cd $SYNTACTIC_PATH_EN ; $SYNTACTIC_PATH_EN/parse -xmlin"
	SYNTACTIC_ANALYSIS_FR	= ""
	TERM_TAG_FR		= ""
	TERM_TAG_EN		= ""
        SEMTAG_EN               = "$SEMTAG_EN_DIR/src/AlvisSemTag -c $CANONICAL_DICT -p $PARENT_DICT -o $ONTOLOGY"
        SEMTAG_FR               = ""
        YATEARC                 = "/etc/yatea/yatea.rc"
        YATEAOUTPUT             = "$ALVISTMP"
</NLP_tools>

<CONVERTERS>
text/plain = text2xhtml  <

text/html = 

www/unknown = 
#text/plain ; ; GuessText

text/x-tex = tth -g -w1 -r <  

application/x-tex =  tth -g -w1 -r < 
#text/x-tex ; untex -a -e -giso ; TeXText
#application/x-tex ; untex -a -e -giso ; TeXText
#text/x-tex ;  ; TeX
#application/x-tex ; ; TeX

application/pdf = pdftohtml -i -noframes -nomerge -stdout 
#application/pdf ; pstotext ; Text
application/postscript = pstotext 
application/msword = antiword -t 

application/vnd.ms-excel =  xlhtml -fw 

application/vnd.ms-powerpoint = ppthtml 
application/powerpoint = ppthtml 

application/rtf = unrtf --nopict --html 
# image/gif ; ; Image
# image/jpeg ; ; Image
# image/tiff ; ; Image
application/xml = 

<STYLESHEET>

default = xsltproc /etc/alvis-nlpplatform/xsl/Default.xsl

</STYLESHEET>

SupplMagicFile = /etc/alvis-nlpplatform/mime/magic.TeX

StoreInputFiles = 0

</CONVERTERS>