File size: 13,757 Bytes
ced4316 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 |
from datetime import datetime
from typing import Any, Dict, List, Optional
S2ORC_NAME_STRING = "S2ORC"
S2ORC_VERSION_STRING = "1.0.0"
CORRECT_KEYS = {"issn": "issue", "type": "type_str"}
SKIP_KEYS = {"link", "bib_id"}
REFERENCE_OUTPUT_KEYS = {
"figure": {"text", "type_str", "uris", "num", "fig_num"},
"table": {"text", "type_str", "content", "num", "html"},
"footnote": {"text", "type_str", "num"},
"section": {"text", "type_str", "num", "parent"},
"equation": {"text", "type_str", "latex", "mathml", "num"},
}
METADATA_KEYS = {"title", "authors", "year", "venue", "identifiers"}
class ReferenceEntry:
"""
Class for representing S2ORC figure and table references
An example json representation (values are examples, not accurate):
{
"FIGREF0": {
"text": "FIG. 2. Depth profiles of...",
"latex": null,
"type": "figure"
},
"TABREF2": {
"text": "Diversity indices of...",
"latex": null,
"type": "table",
"content": "",
"html": ""
}
}
"""
def __init__(
self,
ref_id: str,
text: str,
type_str: str,
latex: Optional[str] = None,
mathml: Optional[str] = None,
content: Optional[str] = None,
html: Optional[str] = None,
uris: Optional[List[str]] = None,
num: Optional[str] = None,
parent: Optional[str] = None,
fig_num: Optional[str] = None,
):
self.ref_id = ref_id
self.text = text
self.type_str = type_str
self.latex = latex
self.mathml = mathml
self.content = content
self.html = html
self.uris = uris
self.num = num
self.parent = parent
self.fig_num = fig_num
def as_json(self):
keep_keys = REFERENCE_OUTPUT_KEYS.get(self.type_str, None)
if keep_keys:
return {k: self.__getattribute__(k) for k in keep_keys}
else:
return {
"text": self.text,
"type": self.type_str,
"latex": self.latex,
"mathml": self.mathml,
"content": self.content,
"html": self.html,
"uris": self.uris,
"num": self.num,
"parent": self.parent,
"fig_num": self.fig_num,
}
class BibliographyEntry:
"""
Class for representing S2ORC parsed bibliography entries
An example json representation (values are examples, not accurate):
{
"title": "Mobility Reports...",
"authors": [
{
"first": "A",
"middle": ["A"],
"last": "Haija",
"suffix": ""
}
],
"year": 2015,
"venue": "IEEE Wireless Commune Mag",
"volume": "42",
"issn": "9",
"pages": "80--92",
"other_ids": {
"doi": [
"10.1109/TWC.2014.2360196"
],
}
}
"""
def __init__(
self,
bib_id: str,
title: str,
authors: List[Dict[str, str]],
ref_id: Optional[str] = None,
year: Optional[int] = None,
venue: Optional[str] = None,
volume: Optional[str] = None,
issue: Optional[str] = None,
pages: Optional[str] = None,
other_ids: Optional[Dict[str, List]] = None,
num: Optional[int] = None,
urls: Optional[List] = None,
raw_text: Optional[str] = None,
links: Optional[List] = None,
):
self.bib_id = bib_id
self.ref_id = ref_id
self.title = title
self.authors = authors
self.year = year
self.venue = venue
self.volume = volume
self.issue = issue
self.pages = pages
self.other_ids = other_ids
self.num = num
self.urls = urls
self.raw_text = raw_text
self.links = links
def as_json(self):
return {
"ref_id": self.ref_id,
"title": self.title,
"authors": self.authors,
"year": self.year,
"venue": self.venue,
"volume": self.volume,
"issue": self.issue,
"pages": self.pages,
"other_ids": self.other_ids,
"num": self.num,
"urls": self.urls,
"raw_text": self.raw_text,
"links": self.links,
}
class Affiliation:
"""
Class for representing affiliation info
Example:
{
"laboratory": "Key Laboratory of Urban Environment and Health",
"institution": "Chinese Academy of Sciences",
"location": {
"postCode": "361021",
"settlement": "Xiamen",
"country": "People's Republic of China"
}
"""
def __init__(self, laboratory: str, institution: str, location: Dict):
self.laboratory = laboratory
self.institution = institution
self.location = location
def as_json(self):
return {
"laboratory": self.laboratory,
"institution": self.institution,
"location": self.location,
}
class Author:
"""
Class for representing paper authors
Example:
{
"first": "Anyi",
"middle": [],
"last": "Hu",
"suffix": "",
"affiliation": {
"laboratory": "Key Laboratory of Urban Environment and Health",
"institution": "Chinese Academy of Sciences",
"location": {
"postCode": "361021",
"settlement": "Xiamen",
"country": "People's Republic of China"
}
},
"email": ""
}
"""
def __init__(
self,
first: str,
middle: List[str],
last: str,
suffix: str,
affiliation: Optional[Dict] = None,
email: Optional[str] = None,
):
self.first = first
self.middle = middle
self.last = last
self.suffix = suffix
self.affiliation = Affiliation(**affiliation) if affiliation else {}
self.email = email
def as_json(self):
return {
"first": self.first,
"middle": self.middle,
"last": self.last,
"suffix": self.suffix,
"affiliation": self.affiliation.as_json() if self.affiliation else {},
"email": self.email,
}
class Metadata:
"""
Class for representing paper metadata
Example:
{
"title": "Niche Partitioning...",
"authors": [
{
"first": "Anyi",
"middle": [],
"last": "Hu",
"suffix": "",
"affiliation": {
"laboratory": "Key Laboratory of Urban Environment and Health",
"institution": "Chinese Academy of Sciences",
"location": {
"postCode": "361021",
"settlement": "Xiamen",
"country": "People's Republic of China"
}
},
"email": ""
}
],
"year": "2011-11"
}
"""
def __init__(
self,
title: str,
authors: List[Dict],
year: Optional[str] = None,
venue: Optional[str] = None,
identifiers: Optional[Dict] = {},
):
self.title = title
self.authors = [Author(**author) for author in authors]
self.year = year
self.venue = venue
self.identifiers = identifiers
def as_json(self):
return {
"title": self.title,
"authors": [author.as_json() for author in self.authors],
"year": self.year,
"venue": self.venue,
"identifiers": self.identifiers,
}
class Paragraph:
"""
Class for representing a parsed paragraph from Grobid xml
All xml tags are removed from the paragraph text, all figures, equations, and tables are replaced
with a special token that maps to a reference identifier
Citation mention spans and section header are extracted
An example json representation (values are examples, not accurate):
{
"text": "Formal language techniques BID1 may be used to study FORMULA0 (see REF0)...",
"mention_spans": [
{
"start": 27,
"end": 31,
"text": "[1]")
],
"ref_spans": [
{
"start": ,
"end": ,
"text": "Fig. 1"
}
],
"eq_spans": [
{
"start": 53,
"end": 61,
"text": "α = 1",
"latex": "\\alpha = 1",
"ref_id": null
}
],
"section": "Abstract"
}
"""
def __init__(
self,
text: str,
cite_spans: List[Dict],
ref_spans: List[Dict],
eq_spans: Optional[List[Dict]] = [],
section: Optional[Any] = None,
sec_num: Optional[Any] = None,
):
self.text = text
self.cite_spans = cite_spans
self.ref_spans = ref_spans
self.eq_spans = eq_spans
if type(section) is str:
if section:
sec_parts = section.split("::")
section_list = [[None, sec_name] for sec_name in sec_parts]
else:
section_list = None
if section_list and sec_num:
section_list[-1][0] = sec_num
else:
section_list = section
self.section = section_list
def as_json(self):
return {
"text": self.text,
"cite_spans": self.cite_spans,
"ref_spans": self.ref_spans,
"eq_spans": self.eq_spans,
"section": "::".join([sec[1] for sec in self.section]) if self.section else "",
"sec_num": self.section[-1][0] if self.section else None,
}
class Paper:
"""
Class for representing a parsed S2ORC paper
"""
def __init__(
self,
paper_id: str,
pdf_hash: str,
metadata: Dict,
abstract: List[Dict],
body_text: List[Dict],
back_matter: List[Dict],
bib_entries: Dict,
ref_entries: Dict,
):
self.paper_id = paper_id
self.pdf_hash = pdf_hash
self.metadata = Metadata(**metadata)
self.abstract = [Paragraph(**para) for para in abstract]
self.body_text = [Paragraph(**para) for para in body_text]
self.back_matter = [Paragraph(**para) for para in back_matter]
self.bib_entries = [
BibliographyEntry(
bib_id=key,
**{
CORRECT_KEYS[k] if k in CORRECT_KEYS else k: v
for k, v in bib.items()
if k not in SKIP_KEYS
},
)
for key, bib in bib_entries.items()
]
self.ref_entries = [
ReferenceEntry(
ref_id=key,
**{
CORRECT_KEYS[k] if k in CORRECT_KEYS else k: v
for k, v in ref.items()
if k != "ref_id"
},
)
for key, ref in ref_entries.items()
]
def as_json(self):
return {
"paper_id": self.paper_id,
"pdf_hash": self.pdf_hash,
"metadata": self.metadata.as_json(),
"abstract": [para.as_json() for para in self.abstract],
"body_text": [para.as_json() for para in self.body_text],
"back_matter": [para.as_json() for para in self.back_matter],
"bib_entries": {bib.bib_id: bib.as_json() for bib in self.bib_entries},
"ref_entries": {ref.ref_id: ref.as_json() for ref in self.ref_entries},
}
@property
def raw_abstract_text(self) -> str:
"""
Get all the body text joined by a newline
:return:
"""
return "\n".join([para.text for para in self.abstract])
@property
def raw_body_text(self) -> str:
"""
Get all the body text joined by a newline
:return:
"""
return "\n".join([para.text for para in self.body_text])
def release_json(self, doc_type: str = "pdf") -> Dict:
"""
Return in release JSON format
:return:
"""
# TODO: not fully implemented; metadata format is not right; extra keys in some places
release_dict: Dict = {"paper_id": self.paper_id}
release_dict.update(
{
"header": {
"generated_with": f"{S2ORC_NAME_STRING} {S2ORC_VERSION_STRING}",
"date_generated": datetime.now().strftime("%Y-%m-%dT%H:%M:%S.%fZ"),
}
}
)
release_dict.update(self.metadata.as_json())
release_dict.update({"abstract": self.raw_abstract_text})
release_dict.update(
{
f"{doc_type}_parse": {
"paper_id": self.paper_id,
"_pdf_hash": self.pdf_hash,
"abstract": [para.as_json() for para in self.abstract],
"body_text": [para.as_json() for para in self.body_text],
"back_matter": [para.as_json() for para in self.back_matter],
"bib_entries": {bib.bib_id: bib.as_json() for bib in self.bib_entries},
"ref_entries": {ref.ref_id: ref.as_json() for ref in self.ref_entries},
}
}
)
return release_dict
|