Go to the documentation of this file.
35 #include "libfolia/folia.h"
36 #include "ticcutils/LogStream.h"
37 #include "ticcutils/Configuration.h"
38 #include "ticcutils/Unicode.h"
39 #include "timbl/TimblAPI.h"
44 mblemData(
const std::string& l,
const std::string& t ):
47 std::string
getLemma()
const {
return lemma; };
48 std::string
getTag()
const {
return tag; };
56 explicit Mblem( TiCC::LogStream *, TiCC::LogStream * =0 );
58 bool init(
const TiCC::Configuration& );
61 void Classify(
const icu::UnicodeString& );
62 std::vector<std::pair<std::string,std::string> >
getResult()
const;
64 std::string
version()
const {
return _version; };
67 void add_lemmas(
const std::vector<folia::Word*>&,
70 std::string call_server(
const std::string& );
71 void read_transtable(
const std::string& );
72 void create_MBlem_defaults();
73 bool readsettings(
const std::string& dir,
const std::string& fname );
74 bool fill_ts_map(
const std::string& );
75 bool fill_eq_set(
const std::string& );
76 std::string make_instance(
const icu::UnicodeString& in );
77 Timbl::TimblAPI *myLex;
78 std::string punctuation;
82 std::map<std::string,std::string> classMap;
83 std::map<std::string, std::map<std::string, int>> token_strip_map;
84 std::set<std::string> one_one_tags;
85 std::vector<mblemData> mblemResult;
88 std::string POS_tagset;
89 std::string textclass;
93 TiCC::LogStream *errLog;
94 TiCC::LogStream *dbgLog;
95 TiCC::UniFilter *filter;
void Classify(frog_record &)
Definition: mblem_mod.cxx:383
void filterTag(const std::string &)
Definition: mblem_mod.cxx:293
mblemData(const std::string &l, const std::string &t)
Definition: mblem_mod.h:44
~Mblem()
Definition: mblem_mod.cxx:253
std::string getLemma() const
Definition: mblem_mod.h:47
Definition: mblem_mod.h:42
a datastructure to hold all frogged information of one Sentence
Definition: FrogData.h:76
Mblem(TiCC::LogStream *, TiCC::LogStream *=0)
create a Timbl based lemmatizer
Definition: mblem_mod.cxx:55
std::vector< std::pair< std::string, std::string > > getResult() const
Definition: mblem_mod.cxx:696
std::string version() const
Definition: mblem_mod.h:64
std::string getTagset() const
Definition: mblem_mod.h:63
a simple datastructure to hold all frogged information of one word
Definition: FrogData.h:47
bool init(const TiCC::Configuration &)
Definition: mblem_mod.cxx:115
void add_lemmas(const std::vector< folia::Word * > &, const frog_data &) const
Definition: mblem_mod.cxx:706
Definition: mblem_mod.h:54
void add_provenance(folia::Document &, folia::processor *) const
Definition: mblem_mod.cxx:361
void makeUnique()
Definition: mblem_mod.cxx:324
std::string getTag() const
Definition: mblem_mod.h:48