Add support for Universal Dependencies v2.0

lucyio · Mar 3, 2017 · 66e1109 · 66e1109
1 parent 8dff040
commit 66e1109
Show file tree

Hide file tree

Showing 14 changed files with 155 additions and 74 deletions.
diff --git a/spacy/attrs.pyx b/spacy/attrs.pyx
@@ -93,7 +93,7 @@ NAMES = [key for key, value in sorted(IDS.items(), key=lambda item: item[1])]
 
 def intify_attrs(stringy_attrs, strings_map=None, _do_deprecated=False):
     '''Normalize a dictionary of attributes, converting them to ints.
-    
+
     Arguments:
         stringy_attrs (dict):
             Dictionary keyed by attribute string names. Values can be ints or strings.
@@ -125,7 +125,9 @@ def intify_attrs(stringy_attrs, strings_map=None, _do_deprecated=False):
             'VerbForm', 'PronType', 'Aspect', 'Tense', 'PartType', 'Poss',
             'Hyph', 'ConjType', 'NumType', 'Foreign', 'VerbType', 'NounType',
             'Number', 'PronType', 'AdjType', 'Person', 'Variant', 'AdpType',
-            'Reflex', 'Negative', 'Mood', 'Aspect', 'Case']
+            'Reflex', 'Negative', 'Mood', 'Aspect', 'Case',
+            'Polarity', # U20
+        ]
         for key in morph_keys:
             if key in stringy_attrs:
                 stringy_attrs.pop(key)

diff --git a/spacy/de/tag_map.py b/spacy/de/tag_map.py
@@ -41,7 +41,7 @@
     "PRF":      {POS: PRON, "PronType": "prs", "Reflex": "yes"},
     "PTKA":     {POS: PART},
     "PTKANT":   {POS: PART, "PartType": "res"},
-    "PTKNEG":   {POS: PART, "Negative": "yes"},
+    "PTKNEG":   {POS: PART, "Polarity": "Neg"},
     "PTKVZ":    {POS: PART, "PartType": "vbp"},
     "PTKZU":    {POS: PART, "PartType": "inf"},
     "PWAT":     {POS: DET, "PronType": "int"},

diff --git a/spacy/en/tag_map.py b/spacy/en/tag_map.py
@@ -16,7 +16,7 @@
     "$":        {POS: SYM, "Other": {"SymType": "currency"}},
     "#":        {POS: SYM, "Other": {"SymType": "numbersign"}},
     "AFX":      {POS: ADJ,  "Hyph": "yes"},
-    "CC":       {POS: CONJ, "ConjType": "coor"},
+    "CC":       {POS: CCONJ, "ConjType": "coor"},
     "CD":       {POS: NUM, "NumType": "card"},
     "DT":       {POS: DET},
     "EX":       {POS: ADV, "AdvType": "ex"},

diff --git a/spacy/language_data/tag_map.py b/spacy/language_data/tag_map.py
@@ -19,6 +19,7 @@
     "AUX":      {POS: AUX},
     "X":        {POS: X},
     "CONJ":     {POS: CONJ},
+    "CCONJ":    {POS: CCONJ}, # U20
     "ADJ":      {POS: ADJ},
     "VERB":     {POS: VERB},
     "PART":     {POS: PART}

diff --git a/spacy/morphology.pxd b/spacy/morphology.pxd
@@ -37,7 +37,7 @@ cdef class Morphology:
     cdef int assign_tag(self, TokenC* token, tag) except -1
 
     cdef int assign_tag_id(self, TokenC* token, int tag_id) except -1
-    
+
     cdef int assign_feature(self, uint64_t* morph, univ_morph_t feat_id, bint value) except -1
 
 
@@ -80,6 +80,7 @@ cpdef enum univ_morph_t:
     Definite_two
     Definite_def
     Definite_red
+    Definite_cons # U20
     Definite_ind
     Degree_cmp
     Degree_comp
@@ -103,6 +104,8 @@ cpdef enum univ_morph_t:
     Negative_neg
     Negative_pos
     Negative_yes
+    Polarity_neg # U20
+    Polarity_pos # U20
     Number_com
     Number_dual
     Number_none
@@ -151,6 +154,7 @@ cpdef enum univ_morph_t:
     VerbForm_partPres
     VerbForm_sup
     VerbForm_trans
+    VerbForm_conv # U20
     VerbForm_gdv # la
     Voice_act
     Voice_cau

diff --git a/spacy/morphology.pyx b/spacy/morphology.pyx
@@ -192,6 +192,7 @@ IDS = {
     "Definite_two": Definite_two,
     "Definite_def": Definite_def,
     "Definite_red": Definite_red,
+    "Definite_cons": Definite_cons, # U20
     "Definite_ind": Definite_ind,
     "Degree_cmp": Degree_cmp,
     "Degree_comp": Degree_comp,
@@ -215,6 +216,8 @@ IDS = {
     "Negative_neg": Negative_neg,
     "Negative_pos": Negative_pos,
     "Negative_yes": Negative_yes,
+    "Polarity_neg": Polarity_neg, # U20
+    "Polarity_pos": Polarity_pos, # U20
     "Number_com": Number_com,
     "Number_dual": Number_dual,
     "Number_none": Number_none,
@@ -263,6 +266,7 @@ IDS = {
     "VerbForm_partPres": VerbForm_partPres,
     "VerbForm_sup": VerbForm_sup,
     "VerbForm_trans": VerbForm_trans,
+    "VerbForm_conv": VerbForm_conv, # U20
     "VerbForm_gdv ": VerbForm_gdv, # la,
     "Voice_act": Voice_act,
     "Voice_cau": Voice_cau,

diff --git a/spacy/parts_of_speech.pxd b/spacy/parts_of_speech.pxd
@@ -7,6 +7,7 @@ cpdef enum univ_pos_t:
     ADV
     AUX
     CONJ
+    CCONJ # U20
     DET
     INTJ
     NOUN

diff --git a/spacy/parts_of_speech.pyx b/spacy/parts_of_speech.pyx
@@ -7,7 +7,8 @@ IDS = {
     "ADP": ADP,
     "ADV": ADV,
     "AUX": AUX,
-    "CONJ": CONJ,
+    "CONJ": CONJ, # U20
+    "CCONJ": CCONJ,
     "DET": DET,
     "INTJ": INTJ,
     "NOUN": NOUN,

diff --git a/spacy/symbols.pxd b/spacy/symbols.pxd
@@ -13,7 +13,7 @@ cpdef enum symbol_t:
     LIKE_EMAIL
     IS_STOP
     IS_OOV
-    
+
     FLAG14 = 14
     FLAG15
     FLAG16
@@ -90,6 +90,7 @@ cpdef enum symbol_t:
     ADV
     AUX
     CONJ
+    CCONJ # U20
     DET
     INTJ
     NOUN
@@ -107,11 +108,14 @@ cpdef enum symbol_t:
 
     Animacy_anim
     Animacy_inam
+    Animacy_hum # U20
     Aspect_freq
     Aspect_imp
     Aspect_mod
     Aspect_none
     Aspect_perf
+    Aspect_iter # U20
+    Aspect_hab # U20
     Case_abe
     Case_abl
     Case_abs
@@ -120,10 +124,12 @@ cpdef enum symbol_t:
     Case_all
     Case_cau
     Case_com
+    Case_cmp # U20
     Case_dat
     Case_del
     Case_dis
     Case_ela
+    Case_equ # U20
     Case_ess
     Case_gen
     Case_ill
@@ -142,7 +148,9 @@ cpdef enum symbol_t:
     Definite_two
     Definite_def
     Definite_red
+    Definite_cons # U20
     Definite_ind
+    Definite_spec # U20
     Degree_cmp
     Degree_comp
     Degree_none
@@ -151,6 +159,8 @@ cpdef enum symbol_t:
     Degree_abs
     Degree_com
     Degree_dim # du
+    Degree_equ # U20
+    Evident_nfh # U20
     Gender_com
     Gender_fem
     Gender_masc
@@ -162,16 +172,21 @@ cpdef enum symbol_t:
     Mood_pot
     Mood_sub
     Mood_opt
+    Mood_prp # U20
+    Mood_adm # U20
     Negative_neg
     Negative_pos
     Negative_yes
+    Polarity_neg # U20
+    Polarity_pos # U20
     Number_com
     Number_dual
     Number_none
     Number_plur
     Number_sing
     Number_ptan # bg
-    Number_count # bg
+    Number_count # bg, U20
+    Number_tri # U20
     NumType_card
     NumType_dist
     NumType_frac
@@ -197,7 +212,8 @@ cpdef enum symbol_t:
     PronType_rel
     PronType_tot
     PronType_clit
-    PronType_exc # es, ca, it, fa
+    PronType_exc # es, ca, it, fa, U20
+    PronType_emp # U20
     Reflex_yes
     Tense_fut
     Tense_imp
@@ -213,12 +229,17 @@ cpdef enum symbol_t:
     VerbForm_partPres
     VerbForm_sup
     VerbForm_trans
+    VerbForm_conv # U20
     VerbForm_gdv # la
+    VerbForm_vnoun # U20
     Voice_act
     Voice_cau
     Voice_pass
-    Voice_mid # gkc
+    Voice_mid # gkc, U20
     Voice_int # hb
+    Voice_antip # U20
+    Voice_dir # U20
+    Voice_inv # U20
     Abbr_yes # cz, fi, sl, U
     AdpType_prep # cz, U
     AdpType_post # U
@@ -284,6 +305,10 @@ cpdef enum symbol_t:
     Number_psee_plur # U
     Number_psor_sing # cz, fi, sl, U
     Number_psor_plur # cz, fi, sl, U
+    Number_pauc # U20
+    Number_grpa # U20
+    Number_grpl # U20
+    Number_inv # U20
     NumForm_digit # cz, sl, U
     NumForm_roman # cz, sl, U
     NumForm_word # cz, sl, U
@@ -311,6 +336,8 @@ cpdef enum symbol_t:
     Person_psor_one # fi, U
     Person_psor_two # fi, U
     Person_psor_three # fi, U
+    Person_zero # U20
+    Person_four # U20
     Polite_inf # bq, U
     Polite_pol # bq, U
     Polite_abs_inf # bq, U
@@ -319,6 +346,10 @@ cpdef enum symbol_t:
     Polite_erg_pol # bq, U
     Polite_dat_inf # bq, U
     Polite_dat_pol # bq, U
+    Polite_infm # U20
+    Polite_form # U20
+    Polite_form_elev # U20
+    Polite_form_humb # U20
     Prefix_yes # U
     PrepCase_npr # cz
     PrepCase_pre # U
@@ -383,6 +414,7 @@ cpdef enum symbol_t:
     ccomp
     complm
     conj
+    cop # U20
     csubj
     csubjpass
     dep
@@ -405,6 +437,8 @@ cpdef enum symbol_t:
     num
     number
     oprd
+    obj # U20
+    obl # U20
     parataxis
     partmod
     pcomp
-Original file line number
+Diff line change
@@ Expand Up / @@ -7,6 +7,7 @@ cpdef enum univ_pos_t: @@
         ADV
         AUX
         CONJ
+        CCONJ # U20
         DET
         INTJ
         NOUN
@@ Expand Down @@