2017-09-16 13:20:04 +03:00
|
|
|
cdef enum symbol_t:
|
2015-10-10 14:11:38 +03:00
|
|
|
NIL
|
|
|
|
|
IS_ALPHA
|
|
|
|
|
IS_ASCII
|
|
|
|
|
IS_DIGIT
|
|
|
|
|
IS_LOWER
|
|
|
|
|
IS_PUNCT
|
|
|
|
|
IS_SPACE
|
|
|
|
|
IS_TITLE
|
|
|
|
|
IS_UPPER
|
|
|
|
|
LIKE_URL
|
|
|
|
|
LIKE_NUM
|
|
|
|
|
LIKE_EMAIL
|
|
|
|
|
IS_STOP
|
|
|
|
|
IS_OOV
|
2017-10-20 14:08:44 +03:00
|
|
|
IS_BRACKET
|
|
|
|
|
IS_QUOTE
|
|
|
|
|
IS_LEFT_PUNCT
|
|
|
|
|
IS_RIGHT_PUNCT
|
2017-02-27 00:27:11 +03:00
|
|
|
|
2017-10-20 14:08:44 +03:00
|
|
|
FLAG18 = 18
|
2015-10-10 14:11:38 +03:00
|
|
|
FLAG19
|
|
|
|
|
FLAG20
|
|
|
|
|
FLAG21
|
|
|
|
|
FLAG22
|
|
|
|
|
FLAG23
|
|
|
|
|
FLAG24
|
|
|
|
|
FLAG25
|
|
|
|
|
FLAG26
|
|
|
|
|
FLAG27
|
|
|
|
|
FLAG28
|
|
|
|
|
FLAG29
|
|
|
|
|
FLAG30
|
|
|
|
|
FLAG31
|
|
|
|
|
FLAG32
|
|
|
|
|
FLAG33
|
|
|
|
|
FLAG34
|
|
|
|
|
FLAG35
|
|
|
|
|
FLAG36
|
|
|
|
|
FLAG37
|
|
|
|
|
FLAG38
|
|
|
|
|
FLAG39
|
|
|
|
|
FLAG40
|
|
|
|
|
FLAG41
|
|
|
|
|
FLAG42
|
|
|
|
|
FLAG43
|
|
|
|
|
FLAG44
|
|
|
|
|
FLAG45
|
|
|
|
|
FLAG46
|
|
|
|
|
FLAG47
|
|
|
|
|
FLAG48
|
|
|
|
|
FLAG49
|
|
|
|
|
FLAG50
|
|
|
|
|
FLAG51
|
|
|
|
|
FLAG52
|
|
|
|
|
FLAG53
|
|
|
|
|
FLAG54
|
|
|
|
|
FLAG55
|
|
|
|
|
FLAG56
|
|
|
|
|
FLAG57
|
|
|
|
|
FLAG58
|
|
|
|
|
FLAG59
|
|
|
|
|
FLAG60
|
|
|
|
|
FLAG61
|
|
|
|
|
FLAG62
|
|
|
|
|
FLAG63
|
2015-10-06 16:41:17 +03:00
|
|
|
|
2015-10-10 14:11:38 +03:00
|
|
|
ID
|
|
|
|
|
ORTH
|
|
|
|
|
LOWER
|
|
|
|
|
NORM
|
|
|
|
|
SHAPE
|
|
|
|
|
PREFIX
|
|
|
|
|
SUFFIX
|
2015-10-06 16:41:17 +03:00
|
|
|
|
2015-10-10 14:11:38 +03:00
|
|
|
LENGTH
|
|
|
|
|
CLUSTER
|
|
|
|
|
LEMMA
|
|
|
|
|
POS
|
|
|
|
|
TAG
|
|
|
|
|
DEP
|
|
|
|
|
ENT_IOB
|
|
|
|
|
ENT_TYPE
|
|
|
|
|
HEAD
|
2016-05-05 13:11:57 +03:00
|
|
|
SENT_START
|
2015-10-10 14:11:38 +03:00
|
|
|
SPACY
|
|
|
|
|
PROB
|
2015-10-06 16:41:17 +03:00
|
|
|
|
2015-10-10 14:11:38 +03:00
|
|
|
ADJ
|
|
|
|
|
ADP
|
|
|
|
|
ADV
|
|
|
|
|
AUX
|
|
|
|
|
CONJ
|
2017-02-27 00:27:11 +03:00
|
|
|
CCONJ # U20
|
2015-10-10 14:11:38 +03:00
|
|
|
DET
|
|
|
|
|
INTJ
|
|
|
|
|
NOUN
|
|
|
|
|
NUM
|
|
|
|
|
PART
|
|
|
|
|
PRON
|
|
|
|
|
PROPN
|
|
|
|
|
PUNCT
|
|
|
|
|
SCONJ
|
|
|
|
|
SYM
|
|
|
|
|
VERB
|
|
|
|
|
X
|
|
|
|
|
EOL
|
|
|
|
|
SPACE
|
2015-10-06 16:41:17 +03:00
|
|
|
|
|
|
|
|
Animacy_anim
|
|
|
|
|
Animacy_inam
|
2017-02-27 00:27:11 +03:00
|
|
|
Animacy_hum # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Aspect_freq
|
|
|
|
|
Aspect_imp
|
|
|
|
|
Aspect_mod
|
|
|
|
|
Aspect_none
|
|
|
|
|
Aspect_perf
|
2017-02-27 00:27:11 +03:00
|
|
|
Aspect_iter # U20
|
|
|
|
|
Aspect_hab # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Case_abe
|
|
|
|
|
Case_abl
|
|
|
|
|
Case_abs
|
|
|
|
|
Case_acc
|
|
|
|
|
Case_ade
|
|
|
|
|
Case_all
|
|
|
|
|
Case_cau
|
|
|
|
|
Case_com
|
2017-02-27 00:27:11 +03:00
|
|
|
Case_cmp # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Case_dat
|
|
|
|
|
Case_del
|
|
|
|
|
Case_dis
|
|
|
|
|
Case_ela
|
2017-02-27 00:27:11 +03:00
|
|
|
Case_equ # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Case_ess
|
|
|
|
|
Case_gen
|
|
|
|
|
Case_ill
|
|
|
|
|
Case_ine
|
|
|
|
|
Case_ins
|
|
|
|
|
Case_loc
|
|
|
|
|
Case_lat
|
|
|
|
|
Case_nom
|
|
|
|
|
Case_par
|
|
|
|
|
Case_sub
|
|
|
|
|
Case_sup
|
|
|
|
|
Case_tem
|
|
|
|
|
Case_ter
|
|
|
|
|
Case_tra
|
|
|
|
|
Case_voc
|
|
|
|
|
Definite_two
|
|
|
|
|
Definite_def
|
|
|
|
|
Definite_red
|
2017-02-27 00:27:11 +03:00
|
|
|
Definite_cons # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Definite_ind
|
2017-02-27 00:27:11 +03:00
|
|
|
Definite_spec # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Degree_cmp
|
|
|
|
|
Degree_comp
|
|
|
|
|
Degree_none
|
|
|
|
|
Degree_pos
|
|
|
|
|
Degree_sup
|
|
|
|
|
Degree_abs
|
|
|
|
|
Degree_com
|
|
|
|
|
Degree_dim # du
|
2017-02-27 00:27:11 +03:00
|
|
|
Degree_equ # U20
|
|
|
|
|
Evident_nfh # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Gender_com
|
|
|
|
|
Gender_fem
|
|
|
|
|
Gender_masc
|
|
|
|
|
Gender_neut
|
|
|
|
|
Mood_cnd
|
|
|
|
|
Mood_imp
|
|
|
|
|
Mood_ind
|
|
|
|
|
Mood_n
|
|
|
|
|
Mood_pot
|
|
|
|
|
Mood_sub
|
|
|
|
|
Mood_opt
|
2017-02-27 00:27:11 +03:00
|
|
|
Mood_prp # U20
|
|
|
|
|
Mood_adm # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Negative_neg
|
|
|
|
|
Negative_pos
|
|
|
|
|
Negative_yes
|
2017-02-27 00:27:11 +03:00
|
|
|
Polarity_neg # U20
|
|
|
|
|
Polarity_pos # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Number_com
|
|
|
|
|
Number_dual
|
|
|
|
|
Number_none
|
|
|
|
|
Number_plur
|
|
|
|
|
Number_sing
|
|
|
|
|
Number_ptan # bg
|
2017-02-27 00:27:11 +03:00
|
|
|
Number_count # bg, U20
|
|
|
|
|
Number_tri # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
NumType_card
|
|
|
|
|
NumType_dist
|
|
|
|
|
NumType_frac
|
|
|
|
|
NumType_gen
|
|
|
|
|
NumType_mult
|
|
|
|
|
NumType_none
|
|
|
|
|
NumType_ord
|
|
|
|
|
NumType_sets
|
|
|
|
|
Person_one
|
|
|
|
|
Person_two
|
|
|
|
|
Person_three
|
|
|
|
|
Person_none
|
|
|
|
|
Poss_yes
|
|
|
|
|
PronType_advPart
|
|
|
|
|
PronType_art
|
|
|
|
|
PronType_default
|
|
|
|
|
PronType_dem
|
|
|
|
|
PronType_ind
|
|
|
|
|
PronType_int
|
|
|
|
|
PronType_neg
|
|
|
|
|
PronType_prs
|
|
|
|
|
PronType_rcp
|
|
|
|
|
PronType_rel
|
|
|
|
|
PronType_tot
|
|
|
|
|
PronType_clit
|
2017-02-27 00:27:11 +03:00
|
|
|
PronType_exc # es, ca, it, fa, U20
|
|
|
|
|
PronType_emp # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Reflex_yes
|
|
|
|
|
Tense_fut
|
|
|
|
|
Tense_imp
|
|
|
|
|
Tense_past
|
|
|
|
|
Tense_pres
|
|
|
|
|
VerbForm_fin
|
|
|
|
|
VerbForm_ger
|
|
|
|
|
VerbForm_inf
|
|
|
|
|
VerbForm_none
|
|
|
|
|
VerbForm_part
|
|
|
|
|
VerbForm_partFut
|
|
|
|
|
VerbForm_partPast
|
|
|
|
|
VerbForm_partPres
|
|
|
|
|
VerbForm_sup
|
|
|
|
|
VerbForm_trans
|
2017-02-27 00:27:11 +03:00
|
|
|
VerbForm_conv # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
VerbForm_gdv # la
|
2017-02-27 00:27:11 +03:00
|
|
|
VerbForm_vnoun # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Voice_act
|
|
|
|
|
Voice_cau
|
|
|
|
|
Voice_pass
|
2017-02-27 00:27:11 +03:00
|
|
|
Voice_mid # gkc, U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Voice_int # hb
|
2017-02-27 00:27:11 +03:00
|
|
|
Voice_antip # U20
|
|
|
|
|
Voice_dir # U20
|
|
|
|
|
Voice_inv # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Abbr_yes # cz, fi, sl, U
|
|
|
|
|
AdpType_prep # cz, U
|
|
|
|
|
AdpType_post # U
|
|
|
|
|
AdpType_voc # cz
|
|
|
|
|
AdpType_comprep # cz
|
|
|
|
|
AdpType_circ # U
|
|
|
|
|
AdvType_man
|
|
|
|
|
AdvType_loc
|
|
|
|
|
AdvType_tim
|
|
|
|
|
AdvType_deg
|
|
|
|
|
AdvType_cau
|
|
|
|
|
AdvType_mod
|
|
|
|
|
AdvType_sta
|
|
|
|
|
AdvType_ex
|
|
|
|
|
AdvType_adadj
|
|
|
|
|
ConjType_oper # cz, U
|
|
|
|
|
ConjType_comp # cz, U
|
|
|
|
|
Connegative_yes # fi
|
|
|
|
|
Derivation_minen # fi
|
|
|
|
|
Derivation_sti # fi
|
|
|
|
|
Derivation_inen # fi
|
|
|
|
|
Derivation_lainen # fi
|
|
|
|
|
Derivation_ja # fi
|
|
|
|
|
Derivation_ton # fi
|
|
|
|
|
Derivation_vs # fi
|
|
|
|
|
Derivation_ttain # fi
|
|
|
|
|
Derivation_ttaa # fi
|
|
|
|
|
Echo_rdp # U
|
|
|
|
|
Echo_ech # U
|
|
|
|
|
Foreign_foreign # cz, fi, U
|
|
|
|
|
Foreign_fscript # cz, fi, U
|
|
|
|
|
Foreign_tscript # cz, U
|
|
|
|
|
Foreign_yes # sl
|
|
|
|
|
Gender_dat_masc # bq, U
|
|
|
|
|
Gender_dat_fem # bq, U
|
|
|
|
|
Gender_erg_masc # bq
|
|
|
|
|
Gender_erg_fem # bq
|
|
|
|
|
Gender_psor_masc # cz, sl, U
|
|
|
|
|
Gender_psor_fem # cz, sl, U
|
|
|
|
|
Gender_psor_neut # sl
|
|
|
|
|
Hyph_yes # cz, U
|
|
|
|
|
InfForm_one # fi
|
|
|
|
|
InfForm_two # fi
|
|
|
|
|
InfForm_three # fi
|
|
|
|
|
NameType_geo # U, cz
|
|
|
|
|
NameType_prs # U, cz
|
|
|
|
|
NameType_giv # U, cz
|
|
|
|
|
NameType_sur # U, cz
|
|
|
|
|
NameType_nat # U, cz
|
|
|
|
|
NameType_com # U, cz
|
|
|
|
|
NameType_pro # U, cz
|
|
|
|
|
NameType_oth # U, cz
|
|
|
|
|
NounType_com # U
|
|
|
|
|
NounType_prop # U
|
|
|
|
|
NounType_class # U
|
|
|
|
|
Number_abs_sing # bq, U
|
|
|
|
|
Number_abs_plur # bq, U
|
|
|
|
|
Number_dat_sing # bq, U
|
|
|
|
|
Number_dat_plur # bq, U
|
|
|
|
|
Number_erg_sing # bq, U
|
|
|
|
|
Number_erg_plur # bq, U
|
|
|
|
|
Number_psee_sing # U
|
|
|
|
|
Number_psee_plur # U
|
|
|
|
|
Number_psor_sing # cz, fi, sl, U
|
|
|
|
|
Number_psor_plur # cz, fi, sl, U
|
2017-02-27 00:27:11 +03:00
|
|
|
Number_pauc # U20
|
|
|
|
|
Number_grpa # U20
|
|
|
|
|
Number_grpl # U20
|
|
|
|
|
Number_inv # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
NumForm_digit # cz, sl, U
|
|
|
|
|
NumForm_roman # cz, sl, U
|
|
|
|
|
NumForm_word # cz, sl, U
|
|
|
|
|
NumValue_one # cz, U
|
|
|
|
|
NumValue_two # cz, U
|
|
|
|
|
NumValue_three # cz, U
|
|
|
|
|
PartForm_pres # fi
|
|
|
|
|
PartForm_past # fi
|
|
|
|
|
PartForm_agt # fi
|
|
|
|
|
PartForm_neg # fi
|
|
|
|
|
PartType_mod # U
|
|
|
|
|
PartType_emp # U
|
|
|
|
|
PartType_res # U
|
|
|
|
|
PartType_inf # U
|
|
|
|
|
PartType_vbp # U
|
|
|
|
|
Person_abs_one # bq, U
|
|
|
|
|
Person_abs_two # bq, U
|
|
|
|
|
Person_abs_three # bq, U
|
|
|
|
|
Person_dat_one # bq, U
|
|
|
|
|
Person_dat_two # bq, U
|
|
|
|
|
Person_dat_three # bq, U
|
|
|
|
|
Person_erg_one # bq, U
|
|
|
|
|
Person_erg_two # bq, U
|
|
|
|
|
Person_erg_three # bq, U
|
|
|
|
|
Person_psor_one # fi, U
|
|
|
|
|
Person_psor_two # fi, U
|
|
|
|
|
Person_psor_three # fi, U
|
2017-02-27 00:27:11 +03:00
|
|
|
Person_zero # U20
|
|
|
|
|
Person_four # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Polite_inf # bq, U
|
|
|
|
|
Polite_pol # bq, U
|
|
|
|
|
Polite_abs_inf # bq, U
|
|
|
|
|
Polite_abs_pol # bq, U
|
|
|
|
|
Polite_erg_inf # bq, U
|
|
|
|
|
Polite_erg_pol # bq, U
|
|
|
|
|
Polite_dat_inf # bq, U
|
|
|
|
|
Polite_dat_pol # bq, U
|
2017-02-27 00:27:11 +03:00
|
|
|
Polite_infm # U20
|
|
|
|
|
Polite_form # U20
|
|
|
|
|
Polite_form_elev # U20
|
|
|
|
|
Polite_form_humb # U20
|
2015-10-06 16:41:17 +03:00
|
|
|
Prefix_yes # U
|
|
|
|
|
PrepCase_npr # cz
|
|
|
|
|
PrepCase_pre # U
|
|
|
|
|
PunctSide_ini # U
|
|
|
|
|
PunctSide_fin # U
|
|
|
|
|
PunctType_peri # U
|
|
|
|
|
PunctType_qest # U
|
|
|
|
|
PunctType_excl # U
|
|
|
|
|
PunctType_quot # U
|
|
|
|
|
PunctType_brck # U
|
|
|
|
|
PunctType_comm # U
|
|
|
|
|
PunctType_colo # U
|
|
|
|
|
PunctType_semi # U
|
|
|
|
|
PunctType_dash # U
|
|
|
|
|
Style_arch # cz, fi, U
|
|
|
|
|
Style_rare # cz, fi, U
|
|
|
|
|
Style_poet # cz, U
|
|
|
|
|
Style_norm # cz, U
|
|
|
|
|
Style_coll # cz, U
|
|
|
|
|
Style_vrnc # cz, U
|
|
|
|
|
Style_sing # cz, U
|
|
|
|
|
Style_expr # cz, U
|
|
|
|
|
Style_derg # cz, U
|
|
|
|
|
Style_vulg # cz, U
|
|
|
|
|
Style_yes # fi, U
|
|
|
|
|
StyleVariant_styleShort # cz
|
|
|
|
|
StyleVariant_styleBound # cz, sl
|
|
|
|
|
VerbType_aux # U
|
|
|
|
|
VerbType_cop # U
|
|
|
|
|
VerbType_mod # U
|
|
|
|
|
VerbType_light # U
|
|
|
|
|
|
2015-10-10 14:59:14 +03:00
|
|
|
PERSON
|
|
|
|
|
NORP
|
|
|
|
|
FACILITY
|
|
|
|
|
ORG
|
|
|
|
|
GPE
|
|
|
|
|
LOC
|
|
|
|
|
PRODUCT
|
|
|
|
|
EVENT
|
|
|
|
|
WORK_OF_ART
|
|
|
|
|
LANGUAGE
|
2015-10-06 16:41:17 +03:00
|
|
|
|
2015-10-10 14:59:14 +03:00
|
|
|
DATE
|
|
|
|
|
TIME
|
|
|
|
|
PERCENT
|
|
|
|
|
MONEY
|
|
|
|
|
QUANTITY
|
|
|
|
|
ORDINAL
|
|
|
|
|
CARDINAL
|
2015-10-06 16:41:17 +03:00
|
|
|
|
2015-10-10 14:59:14 +03:00
|
|
|
acomp
|
|
|
|
|
advcl
|
|
|
|
|
advmod
|
|
|
|
|
agent
|
|
|
|
|
amod
|
|
|
|
|
appos
|
|
|
|
|
attr
|
|
|
|
|
aux
|
|
|
|
|
auxpass
|
|
|
|
|
cc
|
|
|
|
|
ccomp
|
|
|
|
|
complm
|
|
|
|
|
conj
|
2017-02-27 00:27:11 +03:00
|
|
|
cop # U20
|
2015-10-10 14:59:14 +03:00
|
|
|
csubj
|
|
|
|
|
csubjpass
|
|
|
|
|
dep
|
|
|
|
|
det
|
|
|
|
|
dobj
|
|
|
|
|
expl
|
|
|
|
|
hmod
|
|
|
|
|
hyph
|
|
|
|
|
infmod
|
|
|
|
|
intj
|
|
|
|
|
iobj
|
|
|
|
|
mark
|
|
|
|
|
meta
|
|
|
|
|
neg
|
|
|
|
|
nmod
|
|
|
|
|
nn
|
|
|
|
|
npadvmod
|
|
|
|
|
nsubj
|
|
|
|
|
nsubjpass
|
|
|
|
|
num
|
|
|
|
|
number
|
|
|
|
|
oprd
|
2017-02-27 00:27:11 +03:00
|
|
|
obj # U20
|
|
|
|
|
obl # U20
|
2015-10-10 14:59:14 +03:00
|
|
|
parataxis
|
|
|
|
|
partmod
|
|
|
|
|
pcomp
|
|
|
|
|
pobj
|
|
|
|
|
poss
|
|
|
|
|
possessive
|
|
|
|
|
preconj
|
|
|
|
|
prep
|
|
|
|
|
prt
|
|
|
|
|
punct
|
|
|
|
|
quantmod
|
|
|
|
|
rcmod
|
|
|
|
|
root
|
|
|
|
|
xcomp
|
2016-02-04 17:49:45 +03:00
|
|
|
|
2017-10-20 14:08:44 +03:00
|
|
|
acl
|
2017-10-20 14:07:57 +03:00
|
|
|
LAW
|
