|
a |
|
b/test-resources/should/doc_parser-0.json |
|
|
1 |
[ |
|
|
2 |
{ |
|
|
3 |
"children": [], |
|
|
4 |
"dep": 430, |
|
|
5 |
"dep_": "nsubjpass", |
|
|
6 |
"ent": 0, |
|
|
7 |
"ent_": "-<N>-", |
|
|
8 |
"ent_iob": 0, |
|
|
9 |
"ent_iob_": "O", |
|
|
10 |
"i": 0, |
|
|
11 |
"i_sent": 0, |
|
|
12 |
"idx": 0, |
|
|
13 |
"is_contraction": false, |
|
|
14 |
"is_ent": false, |
|
|
15 |
"is_pronoun": true, |
|
|
16 |
"is_punctuation": false, |
|
|
17 |
"is_space": false, |
|
|
18 |
"is_stop": true, |
|
|
19 |
"is_superlative": false, |
|
|
20 |
"is_wh": false, |
|
|
21 |
"lemma_": "he", |
|
|
22 |
"lexspan": { |
|
|
23 |
"begin": 0, |
|
|
24 |
"end": 2 |
|
|
25 |
}, |
|
|
26 |
"norm": "He", |
|
|
27 |
"norm_len": 2, |
|
|
28 |
"pos_": "PRON", |
|
|
29 |
"sent_i": 0, |
|
|
30 |
"shape": 12204527652707022206, |
|
|
31 |
"shape_": "Xx", |
|
|
32 |
"tag": 13656873538139661788, |
|
|
33 |
"tag_": "PRP" |
|
|
34 |
}, |
|
|
35 |
{ |
|
|
36 |
"children": [], |
|
|
37 |
"dep": 406, |
|
|
38 |
"dep_": "auxpass", |
|
|
39 |
"ent": 0, |
|
|
40 |
"ent_": "-<N>-", |
|
|
41 |
"ent_iob": 0, |
|
|
42 |
"ent_iob_": "O", |
|
|
43 |
"i": 1, |
|
|
44 |
"i_sent": 1, |
|
|
45 |
"idx": 3, |
|
|
46 |
"is_contraction": false, |
|
|
47 |
"is_ent": false, |
|
|
48 |
"is_pronoun": false, |
|
|
49 |
"is_punctuation": false, |
|
|
50 |
"is_space": false, |
|
|
51 |
"is_stop": true, |
|
|
52 |
"is_superlative": false, |
|
|
53 |
"is_wh": false, |
|
|
54 |
"lemma_": "be", |
|
|
55 |
"lexspan": { |
|
|
56 |
"begin": 3, |
|
|
57 |
"end": 6 |
|
|
58 |
}, |
|
|
59 |
"norm": "was", |
|
|
60 |
"norm_len": 3, |
|
|
61 |
"pos_": "AUX", |
|
|
62 |
"sent_i": 0, |
|
|
63 |
"shape": 4088098365541558500, |
|
|
64 |
"shape_": "xxx", |
|
|
65 |
"tag": 17109001835818727656, |
|
|
66 |
"tag_": "VBD" |
|
|
67 |
}, |
|
|
68 |
{ |
|
|
69 |
"children": [ |
|
|
70 |
0, |
|
|
71 |
1, |
|
|
72 |
3, |
|
|
73 |
9 |
|
|
74 |
], |
|
|
75 |
"dep": 8206900633647566924, |
|
|
76 |
"dep_": "ROOT", |
|
|
77 |
"ent": 0, |
|
|
78 |
"ent_": "-<N>-", |
|
|
79 |
"ent_iob": 0, |
|
|
80 |
"ent_iob_": "O", |
|
|
81 |
"i": 2, |
|
|
82 |
"i_sent": 2, |
|
|
83 |
"idx": 7, |
|
|
84 |
"is_contraction": false, |
|
|
85 |
"is_ent": false, |
|
|
86 |
"is_pronoun": false, |
|
|
87 |
"is_punctuation": false, |
|
|
88 |
"is_space": false, |
|
|
89 |
"is_stop": false, |
|
|
90 |
"is_superlative": false, |
|
|
91 |
"is_wh": false, |
|
|
92 |
"lemma_": "diagnose", |
|
|
93 |
"lexspan": { |
|
|
94 |
"begin": 7, |
|
|
95 |
"end": 16 |
|
|
96 |
}, |
|
|
97 |
"norm": "diagnosed", |
|
|
98 |
"norm_len": 9, |
|
|
99 |
"pos_": "VERB", |
|
|
100 |
"sent_i": 0, |
|
|
101 |
"shape": 13110060611322374290, |
|
|
102 |
"shape_": "xxxx", |
|
|
103 |
"tag": 3822385049556375858, |
|
|
104 |
"tag_": "VBN" |
|
|
105 |
}, |
|
|
106 |
{ |
|
|
107 |
"children": [ |
|
|
108 |
5 |
|
|
109 |
], |
|
|
110 |
"dep": 443, |
|
|
111 |
"dep_": "prep", |
|
|
112 |
"ent": 0, |
|
|
113 |
"ent_": "-<N>-", |
|
|
114 |
"ent_iob": 0, |
|
|
115 |
"ent_iob_": "O", |
|
|
116 |
"i": 3, |
|
|
117 |
"i_sent": 3, |
|
|
118 |
"idx": 17, |
|
|
119 |
"is_contraction": false, |
|
|
120 |
"is_ent": false, |
|
|
121 |
"is_pronoun": false, |
|
|
122 |
"is_punctuation": false, |
|
|
123 |
"is_space": false, |
|
|
124 |
"is_stop": true, |
|
|
125 |
"is_superlative": false, |
|
|
126 |
"is_wh": false, |
|
|
127 |
"lemma_": "with", |
|
|
128 |
"lexspan": { |
|
|
129 |
"begin": 17, |
|
|
130 |
"end": 21 |
|
|
131 |
}, |
|
|
132 |
"norm": "with", |
|
|
133 |
"norm_len": 4, |
|
|
134 |
"pos_": "ADP", |
|
|
135 |
"sent_i": 0, |
|
|
136 |
"shape": 13110060611322374290, |
|
|
137 |
"shape_": "xxxx", |
|
|
138 |
"tag": 1292078113972184607, |
|
|
139 |
"tag_": "IN" |
|
|
140 |
}, |
|
|
141 |
{ |
|
|
142 |
"children": [], |
|
|
143 |
"dep": 7037928807040764755, |
|
|
144 |
"dep_": "compound", |
|
|
145 |
"ent": 0, |
|
|
146 |
"ent_": "-<N>-", |
|
|
147 |
"ent_iob": 0, |
|
|
148 |
"ent_iob_": "O", |
|
|
149 |
"i": 4, |
|
|
150 |
"i_sent": 4, |
|
|
151 |
"idx": 22, |
|
|
152 |
"is_contraction": false, |
|
|
153 |
"is_ent": false, |
|
|
154 |
"is_pronoun": false, |
|
|
155 |
"is_punctuation": false, |
|
|
156 |
"is_space": false, |
|
|
157 |
"is_stop": false, |
|
|
158 |
"is_superlative": false, |
|
|
159 |
"is_wh": false, |
|
|
160 |
"lemma_": "kidney", |
|
|
161 |
"lexspan": { |
|
|
162 |
"begin": 22, |
|
|
163 |
"end": 28 |
|
|
164 |
}, |
|
|
165 |
"norm": "kidney", |
|
|
166 |
"norm_len": 6, |
|
|
167 |
"pos_": "NOUN", |
|
|
168 |
"sent_i": 0, |
|
|
169 |
"shape": 13110060611322374290, |
|
|
170 |
"shape_": "xxxx", |
|
|
171 |
"tag": 15308085513773655218, |
|
|
172 |
"tag_": "NN" |
|
|
173 |
}, |
|
|
174 |
{ |
|
|
175 |
"children": [ |
|
|
176 |
4, |
|
|
177 |
6, |
|
|
178 |
8 |
|
|
179 |
], |
|
|
180 |
"dep": 439, |
|
|
181 |
"dep_": "pobj", |
|
|
182 |
"ent": 0, |
|
|
183 |
"ent_": "-<N>-", |
|
|
184 |
"ent_iob": 0, |
|
|
185 |
"ent_iob_": "O", |
|
|
186 |
"i": 5, |
|
|
187 |
"i_sent": 5, |
|
|
188 |
"idx": 29, |
|
|
189 |
"is_contraction": false, |
|
|
190 |
"is_ent": false, |
|
|
191 |
"is_pronoun": false, |
|
|
192 |
"is_punctuation": false, |
|
|
193 |
"is_space": false, |
|
|
194 |
"is_stop": false, |
|
|
195 |
"is_superlative": false, |
|
|
196 |
"is_wh": false, |
|
|
197 |
"lemma_": "failure", |
|
|
198 |
"lexspan": { |
|
|
199 |
"begin": 29, |
|
|
200 |
"end": 36 |
|
|
201 |
}, |
|
|
202 |
"norm": "failure", |
|
|
203 |
"norm_len": 7, |
|
|
204 |
"pos_": "NOUN", |
|
|
205 |
"sent_i": 0, |
|
|
206 |
"shape": 13110060611322374290, |
|
|
207 |
"shape_": "xxxx", |
|
|
208 |
"tag": 15308085513773655218, |
|
|
209 |
"tag_": "NN" |
|
|
210 |
}, |
|
|
211 |
{ |
|
|
212 |
"children": [], |
|
|
213 |
"dep": 407, |
|
|
214 |
"dep_": "cc", |
|
|
215 |
"ent": 0, |
|
|
216 |
"ent_": "-<N>-", |
|
|
217 |
"ent_iob": 0, |
|
|
218 |
"ent_iob_": "O", |
|
|
219 |
"i": 6, |
|
|
220 |
"i_sent": 6, |
|
|
221 |
"idx": 37, |
|
|
222 |
"is_contraction": false, |
|
|
223 |
"is_ent": false, |
|
|
224 |
"is_pronoun": false, |
|
|
225 |
"is_punctuation": false, |
|
|
226 |
"is_space": false, |
|
|
227 |
"is_stop": true, |
|
|
228 |
"is_superlative": false, |
|
|
229 |
"is_wh": false, |
|
|
230 |
"lemma_": "and", |
|
|
231 |
"lexspan": { |
|
|
232 |
"begin": 37, |
|
|
233 |
"end": 40 |
|
|
234 |
}, |
|
|
235 |
"norm": "and", |
|
|
236 |
"norm_len": 3, |
|
|
237 |
"pos_": "CCONJ", |
|
|
238 |
"sent_i": 0, |
|
|
239 |
"shape": 4088098365541558500, |
|
|
240 |
"shape_": "xxx", |
|
|
241 |
"tag": 17571114184892886314, |
|
|
242 |
"tag_": "CC" |
|
|
243 |
}, |
|
|
244 |
{ |
|
|
245 |
"children": [], |
|
|
246 |
"dep": 7037928807040764755, |
|
|
247 |
"dep_": "compound", |
|
|
248 |
"ent": 0, |
|
|
249 |
"ent_": "-<N>-", |
|
|
250 |
"ent_iob": 0, |
|
|
251 |
"ent_iob_": "O", |
|
|
252 |
"i": 7, |
|
|
253 |
"i_sent": 7, |
|
|
254 |
"idx": 41, |
|
|
255 |
"is_contraction": false, |
|
|
256 |
"is_ent": false, |
|
|
257 |
"is_pronoun": false, |
|
|
258 |
"is_punctuation": false, |
|
|
259 |
"is_space": false, |
|
|
260 |
"is_stop": false, |
|
|
261 |
"is_superlative": false, |
|
|
262 |
"is_wh": false, |
|
|
263 |
"lemma_": "heart", |
|
|
264 |
"lexspan": { |
|
|
265 |
"begin": 41, |
|
|
266 |
"end": 46 |
|
|
267 |
}, |
|
|
268 |
"norm": "heart", |
|
|
269 |
"norm_len": 5, |
|
|
270 |
"pos_": "NOUN", |
|
|
271 |
"sent_i": 0, |
|
|
272 |
"shape": 13110060611322374290, |
|
|
273 |
"shape_": "xxxx", |
|
|
274 |
"tag": 15308085513773655218, |
|
|
275 |
"tag_": "NN" |
|
|
276 |
}, |
|
|
277 |
{ |
|
|
278 |
"children": [ |
|
|
279 |
7 |
|
|
280 |
], |
|
|
281 |
"dep": 410, |
|
|
282 |
"dep_": "conj", |
|
|
283 |
"ent": 0, |
|
|
284 |
"ent_": "-<N>-", |
|
|
285 |
"ent_iob": 0, |
|
|
286 |
"ent_iob_": "O", |
|
|
287 |
"i": 8, |
|
|
288 |
"i_sent": 8, |
|
|
289 |
"idx": 47, |
|
|
290 |
"is_contraction": false, |
|
|
291 |
"is_ent": false, |
|
|
292 |
"is_pronoun": false, |
|
|
293 |
"is_punctuation": false, |
|
|
294 |
"is_space": false, |
|
|
295 |
"is_stop": false, |
|
|
296 |
"is_superlative": false, |
|
|
297 |
"is_wh": false, |
|
|
298 |
"lemma_": "disease", |
|
|
299 |
"lexspan": { |
|
|
300 |
"begin": 47, |
|
|
301 |
"end": 54 |
|
|
302 |
}, |
|
|
303 |
"norm": "disease", |
|
|
304 |
"norm_len": 7, |
|
|
305 |
"pos_": "NOUN", |
|
|
306 |
"sent_i": 0, |
|
|
307 |
"shape": 13110060611322374290, |
|
|
308 |
"shape_": "xxxx", |
|
|
309 |
"tag": 15308085513773655218, |
|
|
310 |
"tag_": "NN" |
|
|
311 |
}, |
|
|
312 |
{ |
|
|
313 |
"children": [], |
|
|
314 |
"dep": 445, |
|
|
315 |
"dep_": "punct", |
|
|
316 |
"ent": 0, |
|
|
317 |
"ent_": "-<N>-", |
|
|
318 |
"ent_iob": 0, |
|
|
319 |
"ent_iob_": "O", |
|
|
320 |
"i": 9, |
|
|
321 |
"i_sent": 9, |
|
|
322 |
"idx": 54, |
|
|
323 |
"is_contraction": false, |
|
|
324 |
"is_ent": false, |
|
|
325 |
"is_pronoun": false, |
|
|
326 |
"is_punctuation": true, |
|
|
327 |
"is_space": false, |
|
|
328 |
"is_stop": false, |
|
|
329 |
"is_superlative": false, |
|
|
330 |
"is_wh": false, |
|
|
331 |
"lemma_": ".", |
|
|
332 |
"lexspan": { |
|
|
333 |
"begin": 54, |
|
|
334 |
"end": 55 |
|
|
335 |
}, |
|
|
336 |
"norm": ".", |
|
|
337 |
"norm_len": 1, |
|
|
338 |
"pos_": "PUNCT", |
|
|
339 |
"sent_i": 0, |
|
|
340 |
"shape": 12646065887601541794, |
|
|
341 |
"shape_": ".", |
|
|
342 |
"tag": 12646065887601541794, |
|
|
343 |
"tag_": "." |
|
|
344 |
} |
|
|
345 |
] |