Skip to content

pyCEURspt API Documentation

bibtex

BibTexConverter

Convert volumes and papers to corresponding bibtex entries

Source code in ceurspt/bibtex.py 
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
class BibTexConverter:
    """
    Convert volumes and papers to corresponding bibtex entries
    """

    @classmethod
    def convert_volume(cls, volume: Volume) -> str:
        """
        convert given volume to biblatex entry
        """
        library = BibDatabase()
        proceedings_entry = ProceedingsEntry.from_volume(volume)
        library.entries.append(proceedings_entry.to_bibtex_record())
        for paper in volume.papers:
            in_proceedings_entry = InProceedingsEntry.from_paper(paper)
            library.entries.append(
                in_proceedings_entry.to_bibtex_record(
                    crossref=proceedings_entry.get_id()
                )
            )
        bibtex = bibtexparser.dumps(library)
        return bibtex

    @classmethod
    def convert_paper(cls, paper: Paper) -> str:
        """
        convert given paper to biblatex entry
        """
        library = BibDatabase()
        in_proceedings_entry = InProceedingsEntry.from_paper(paper)
        library.entries.append(in_proceedings_entry.to_bibtex_record())
        bibtex = bibtexparser.dumps(library)
        return bibtex

convert_paper(paper) classmethod

convert given paper to biblatex entry

Source code in ceurspt/bibtex.py 
278
279
280
281
282
283
284
285
286
287
@classmethod
def convert_paper(cls, paper: Paper) -> str:
    """
    convert given paper to biblatex entry
    """
    library = BibDatabase()
    in_proceedings_entry = InProceedingsEntry.from_paper(paper)
    library.entries.append(in_proceedings_entry.to_bibtex_record())
    bibtex = bibtexparser.dumps(library)
    return bibtex

convert_volume(volume) classmethod

convert given volume to biblatex entry

Source code in ceurspt/bibtex.py 
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
@classmethod
def convert_volume(cls, volume: Volume) -> str:
    """
    convert given volume to biblatex entry
    """
    library = BibDatabase()
    proceedings_entry = ProceedingsEntry.from_volume(volume)
    library.entries.append(proceedings_entry.to_bibtex_record())
    for paper in volume.papers:
        in_proceedings_entry = InProceedingsEntry.from_paper(paper)
        library.entries.append(
            in_proceedings_entry.to_bibtex_record(
                crossref=proceedings_entry.get_id()
            )
        )
    bibtex = bibtexparser.dumps(library)
    return bibtex

InProceedingsEntry dataclass

see https://ftp.mpi-inf.mpg.de/pub/tex/mirror/ftp.dante.de/pub/tex/macros/latex/contrib/biblatex/doc/biblatex.pdf

Source code in ceurspt/bibtex.py 
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
@dataclass
class InProceedingsEntry:
    """
    see https://ftp.mpi-inf.mpg.de/pub/tex/mirror/ftp.dante.de/pub/tex/macros/latex/contrib/biblatex/doc/biblatex.pdf
    """

    title: str
    author: Union[str, List[str]]
    booktitle: str
    year: str
    date: str

    editor: Optional[Union[str, List[str]]] = None
    subtitle: Optional[str] = None
    titleaddon: Optional[str] = None
    maintitle: Optional[str] = None

    mainsubtitle: Optional[str] = None
    maintitleaddon: Optional[str] = None
    booksubtitle: Optional[str] = None
    booktitleaddon: Optional[str] = None

    eventtitle: Optional[str] = None
    eventtitleaddon: Optional[str] = None
    eventdate: Optional[str] = None
    venue: Optional[str] = None
    language: Optional[str] = "english"

    volume: Optional[str] = None
    part: Optional[str] = None
    volumes: Optional[str] = None
    series: Optional[str] = "CEUR Workshop Proceedings"
    number: Optional[str] = None
    note: Optional[str] = None
    organization: Optional[str] = None

    publisher: Optional[str] = None
    location: Optional[str] = "Aachen"
    month: Optional[str] = None
    isbn: Optional[str] = None
    eid: Optional[str] = None
    chapter: Optional[str] = None
    pages: Optional[str] = None
    addendum: Optional[str] = None

    pubstate: Optional[str] = None
    doi: Optional[str] = None
    eprint: Optional[str] = None
    eprintclass: Optional[str] = None
    eprinttype: Optional[str] = None
    url: Optional[str] = None
    urldate: Optional[str] = None

    @classmethod
    def from_paper(cls, paper: Paper) -> "InProceedingsEntry":
        record = paper.getMergedDict()
        pub_date = (
            datetime.fromisoformat(record.get("spt.volume").get("date"))
            if record.get("spt.volume") is not None
            else None
        )
        authors = record.get("cvb.authors", None)
        if authors is not None:
            if isinstance(authors, str):
                authors = authors.replace(",", " and ")
        elif "dblp.authors" in record:
            authors = " and ".join(
                [
                    author_record.get("label")
                    for author_record in record.get("dblp.authors")
                ]
            )
        in_proceedings = InProceedingsEntry(
            title=record.get("spt.title", None),
            author=authors,
            year=str(pub_date.year),
            date=pub_date.date().isoformat(),
            booktitle=record.get("spt.volume", {}).get("title", None),
            url=(
                str(record.get("spt.pdfUrl"))
                if record.get("spt.pdfUrl", None)
                else None
            ),
            volume=str(record.get("spt.volume", {}).get("number")),
        )
        if hasattr(paper, "vm") and isinstance(paper.vm, Volume):
            volume_record = paper.vm.getMergedDict()
            in_proceedings.eventtitle = volume_record.get("wd.eventLabel", None)
            in_proceedings.eventdate = volume_record.get("wd.startDate", None)
            in_proceedings.venue = ",".join(
                filter(
                    partial(is_not, None),
                    [
                        volume_record.get("wd.locationLabel", None),
                        volume_record.get("wd.countryLabel", None),
                    ],
                )
            )
            in_proceedings.editor = volume_record.get("cvb.editors", "").replace(
                ",", " and"
            )
        in_proceedings.__paper = paper
        return in_proceedings

    def to_bibtex_record(self, crossref: Optional[str] = None) -> dict:
        """
        Convert to bibtex compatible dict
        Args:
            crossref: bibtex key of the proceedings. If set the proceeding specific fields are excluded.
        """
        proceedings_keys = [
            "series",
            "location",
            "eventtitle",
            "venue",
            "volume",
            "editor",
            "eventdate",
        ]
        record_fields = {k: v for k, v in asdict(self).items() if v not in [None, ""]}
        if crossref is not None:
            record_fields = {
                k: v for k, v in record_fields.items() if k not in proceedings_keys
            }
            record_fields["crossref"] = crossref
        record = {
            "ENTRYTYPE": "inproceedings",
            "ID": f"ceur-ws:{self.get_id()}",
            **record_fields,
        }
        return record

    def get_id(self) -> str:
        entry_id = None
        try:
            entry_id = (
                self.__paper.getMergedDict().get("spt.id", None).replace("/", ":")
            )
        except KeyError:
            pass
        return entry_id

to_bibtex_record(crossref=None)

Convert to bibtex compatible dict Args: crossref: bibtex key of the proceedings. If set the proceeding specific fields are excluded.

Source code in ceurspt/bibtex.py 
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
def to_bibtex_record(self, crossref: Optional[str] = None) -> dict:
    """
    Convert to bibtex compatible dict
    Args:
        crossref: bibtex key of the proceedings. If set the proceeding specific fields are excluded.
    """
    proceedings_keys = [
        "series",
        "location",
        "eventtitle",
        "venue",
        "volume",
        "editor",
        "eventdate",
    ]
    record_fields = {k: v for k, v in asdict(self).items() if v not in [None, ""]}
    if crossref is not None:
        record_fields = {
            k: v for k, v in record_fields.items() if k not in proceedings_keys
        }
        record_fields["crossref"] = crossref
    record = {
        "ENTRYTYPE": "inproceedings",
        "ID": f"ceur-ws:{self.get_id()}",
        **record_fields,
    }
    return record

ProceedingsEntry dataclass

see https://ftp.mpi-inf.mpg.de/pub/tex/mirror/ftp.dante.de/pub/tex/macros/latex/contrib/biblatex/doc/biblatex.pdf

Source code in ceurspt/bibtex.py 
 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
@dataclass
class ProceedingsEntry:
    """
    see https://ftp.mpi-inf.mpg.de/pub/tex/mirror/ftp.dante.de/pub/tex/macros/latex/contrib/biblatex/doc/biblatex.pdf

    """

    title: str
    year: str
    date: str

    editor: Optional[Union[str, List[str]]] = None
    subtitle: Optional[str] = None
    titleaddon: Optional[str] = None
    maintitle: Optional[str] = None
    mainsubtitle: Optional[str] = None
    maintitleaddon: Optional[str] = None
    eventtitle: Optional[str] = None
    eventtitleaddon: Optional[str] = None
    eventdate: Optional[str] = None
    venue: Optional[str] = None
    language: Optional[str] = "english"
    volume: Optional[str] = None
    part: Optional[str] = None
    volumes: Optional[str] = None
    series: Optional[str] = "CEUR Workshop Proceedings"

    number: Optional[str] = None
    note: Optional[str] = None
    organization: Optional[str] = None
    publisher: Optional[str] = None
    location: Optional[str] = "Aachen"
    month: Optional[str] = None
    isbn: Optional[str] = None

    eid: Optional[str] = None
    chapter: Optional[str] = None
    pages: Optional[str] = None
    pagetotal: Optional[str] = None
    addendum: Optional[str] = None
    pubstate: Optional[str] = None
    doi: Optional[str] = None
    eprint: Optional[str] = None

    eprintclass: Optional[str] = None
    eprinttype: Optional[str] = None
    url: Optional[str] = None
    urldate: Optional[str] = None

    @classmethod
    def from_volume(cls, volume: Volume) -> "ProceedingsEntry":
        """
        Convert given volume to ProceedingsEntry
        """
        record = volume.getMergedDict()
        pub_date = (
            datetime.fromisoformat(record.get("wd.publication_date"))
            if record.get("wd.publication_date") is not None
            else None
        )
        proceeding = ProceedingsEntry(
            title=volume.title,
            date=pub_date.date().isoformat(),
            year=str(pub_date.year) if pub_date else None,
            url=record.get("spt.url"),
            eventtitle=record.get("wd.eventLabel", None),
            eventdate=record.get("wd.startDate", None),
            venue=",".join(
                filter(
                    partial(is_not, None),
                    [
                        record.get("wd.locationLabel", None),
                        record.get("wd.countryLabel", None),
                    ],
                )
            ),
            volume=str(volume.number),
            editor=record.get("cvb.editors", "").replace(",", " and"),
        )
        proceeding.__volume = volume
        return proceeding

    def to_bibtex_record(self) -> dict:
        record = {
            "ENTRYTYPE": "proceedings",
            "ID": self.get_id(),
            **{k: v for k, v in asdict(self).items() if v not in [None, ""]},
        }
        return record

    def get_id(self) -> str:
        entry_id = None
        if hasattr(self, "__volume") and isinstance(self.__volume, Volume):
            entry_id = self.__volume.acronym.replace(" ", "_")
        if entry_id is None:
            entry_id = f"ceur-ws:Vol-{self.volume}"
        return entry_id

from_volume(volume) classmethod

Convert given volume to ProceedingsEntry

Source code in ceurspt/bibtex.py 
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
@classmethod
def from_volume(cls, volume: Volume) -> "ProceedingsEntry":
    """
    Convert given volume to ProceedingsEntry
    """
    record = volume.getMergedDict()
    pub_date = (
        datetime.fromisoformat(record.get("wd.publication_date"))
        if record.get("wd.publication_date") is not None
        else None
    )
    proceeding = ProceedingsEntry(
        title=volume.title,
        date=pub_date.date().isoformat(),
        year=str(pub_date.year) if pub_date else None,
        url=record.get("spt.url"),
        eventtitle=record.get("wd.eventLabel", None),
        eventdate=record.get("wd.startDate", None),
        venue=",".join(
            filter(
                partial(is_not, None),
                [
                    record.get("wd.locationLabel", None),
                    record.get("wd.countryLabel", None),
                ],
            )
        ),
        volume=str(volume.number),
        editor=record.get("cvb.editors", "").replace(",", " and"),
    )
    proceeding.__volume = volume
    return proceeding

ceurws

Created on 2023-03-18

@author: wf

JsonCacheManager

a json based cache manager

Source code in ceurspt/ceurws.py 
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
class JsonCacheManager:
    """
    a json based cache manager
    """

    def __init__(self, base_url: str = "http://cvb.bitplan.com"):
        """
        constructor

        base_url(str): the base url to use for the json provider
        """
        self.base_url = base_url

    def json_path(self, lod_name: str) -> str:
        """
        get the json path for the given list of dicts name

        Args:
            lod_name(str): the name of the list of dicts cache to read

        Returns:
            str: the path to the list of dict cache
        """
        root_path = f"{Path.home()}/.ceurws"
        os.makedirs(root_path, exist_ok=True)
        json_path = f"{root_path}/{lod_name}.json"
        return json_path

    def load_lod(self, lod_name: str) -> list:
        """
        load my list of dicts

        Args:
            lod_name(str): the name of the list of dicts cache to read

        Returns:
            list: the list of dicts
        """
        json_path = self.json_path(lod_name)
        if os.path.isfile(json_path):
            try:
                with open(json_path) as json_file:
                    json_str = json_file.read()
                    lod = orjson.loads(json_str)
            except Exception as ex:
                msg = f"Could not read {lod_name} from {json_path} due to {str(ex)}"
                raise Exception(msg)
        else:
            try:
                url = f"{self.base_url}/{lod_name}.json"
                with urllib.request.urlopen(url) as source:
                    json_str = source.read()
                    lod = orjson.loads(json_str)
            except Exception as ex:
                msg = f"Could not read {lod_name} from {url} due to {str(ex)}"
                raise Exception(msg)
        return lod

    def store(self, lod_name: str, lod: list):
        """
        store my list of dicts

        Args:
            lod_name(str): the name of the list of dicts cache to write
            lod(list): the list of dicts to write
        """
        with open(self.json_path(lod_name), "wb") as json_file:
            json_str = orjson.dumps(lod)
            json_file.write(json_str)
            pass

__init__(base_url='http://cvb.bitplan.com')

constructor

base_url(str): the base url to use for the json provider

Source code in ceurspt/ceurws.py 
943
944
945
946
947
948
949
def __init__(self, base_url: str = "http://cvb.bitplan.com"):
    """
    constructor

    base_url(str): the base url to use for the json provider
    """
    self.base_url = base_url

json_path(lod_name)

get the json path for the given list of dicts name

Parameters:

Name Type Description Default
lod_name(str)

the name of the list of dicts cache to read

 required

Returns:

Name Type Description
str str

the path to the list of dict cache
Source code in ceurspt/ceurws.py 
951
952
953
954
955
956
957
958
959
960
961
962
963
964
def json_path(self, lod_name: str) -> str:
    """
    get the json path for the given list of dicts name

    Args:
        lod_name(str): the name of the list of dicts cache to read

    Returns:
        str: the path to the list of dict cache
    """
    root_path = f"{Path.home()}/.ceurws"
    os.makedirs(root_path, exist_ok=True)
    json_path = f"{root_path}/{lod_name}.json"
    return json_path

load_lod(lod_name)

load my list of dicts

Parameters:

Name Type Description Default
lod_name(str)

the name of the list of dicts cache to read

 required

Returns:

Name Type Description
list list

the list of dicts
Source code in ceurspt/ceurws.py 
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
def load_lod(self, lod_name: str) -> list:
    """
    load my list of dicts

    Args:
        lod_name(str): the name of the list of dicts cache to read

    Returns:
        list: the list of dicts
    """
    json_path = self.json_path(lod_name)
    if os.path.isfile(json_path):
        try:
            with open(json_path) as json_file:
                json_str = json_file.read()
                lod = orjson.loads(json_str)
        except Exception as ex:
            msg = f"Could not read {lod_name} from {json_path} due to {str(ex)}"
            raise Exception(msg)
    else:
        try:
            url = f"{self.base_url}/{lod_name}.json"
            with urllib.request.urlopen(url) as source:
                json_str = source.read()
                lod = orjson.loads(json_str)
        except Exception as ex:
            msg = f"Could not read {lod_name} from {url} due to {str(ex)}"
            raise Exception(msg)
    return lod

store(lod_name, lod)

store my list of dicts

Parameters:

Name Type Description Default
lod_name(str)

the name of the list of dicts cache to write

 required
lod(list)

the list of dicts to write

 required
Source code in ceurspt/ceurws.py 
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
def store(self, lod_name: str, lod: list):
    """
    store my list of dicts

    Args:
        lod_name(str): the name of the list of dicts cache to write
        lod(list): the list of dicts to write
    """
    with open(self.json_path(lod_name), "wb") as json_file:
        json_str = orjson.dumps(lod)
        json_file.write(json_str)
        pass

Paper dataclass

Bases: Paper

a CEUR-WS Paper with it's behavior

Source code in ceurspt/ceurws.py 
 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
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
class Paper(ceurspt.ceurws_base.Paper):
    """
    a CEUR-WS Paper with it's behavior
    """

    def getBasePath(self) -> Optional[str]:
        """
        get the base path to my files
        """
        if self.pdfUrl:
            base_path = self.pdfUrl.replace("https://ceur-ws.org/", "")
            base_path = base_path.replace(".pdf", "")
            base_path = f"{self.volume.vm.base_path}/{base_path}"
            if os.path.isfile(f"{base_path}.pdf"):
                return base_path
        return None

    def getContentPathByPostfix(self, postfix: str):
        """
        get the content path for the given postfix

        Args:
            postfix(str): the postfix to read

        Returns:
            str: the context path
        """
        base_path = self.getBasePath()
        if base_path is None:
            return None
        text_path = f"{base_path}{postfix}"
        if os.path.isfile(text_path):
            return text_path
        else:
            return None

    def getContentByPostfix(self, postfix: str) -> str:
        """
        get the content for the given postfix

        Args:
            postfix(str): the postfix to read

        Returns:
            str: the context
        """
        text_path = self.getContentPathByPostfix(postfix)
        content = None
        if text_path:
            with open(text_path, "r") as text_file:
                content = text_file.read()
        return content

    def getText(self) -> str:
        """
        get the plain text content of this paper
        """
        text = self.getContentByPostfix("-content.txt")
        return text

    def getPdf(self):
        """
        get the PDF file for this paper
        """
        base_path = self.getBasePath()
        pdf = f"{base_path}.pdf"
        return pdf

    def getMergedDict(self) -> dict:
        """
        get the merged dict for this paper
        """
        my_dict = dataclasses.asdict(self)
        m_dict = {
            "version.version": Version.version,
            "version.cm_url": Version.cm_url,
            "spt.html_url": f"/{self.id}.html",
        }
        for key, value in my_dict.items():
            m_dict[f"spt.{key}"] = value
        pdf_name = self.pdfUrl.replace("https://ceur-ws.org/", "")
        if pdf_name in self.pm.paper_records_by_path:
            pdf_record = self.pm.paper_records_by_path[pdf_name]
            for key, value in pdf_record.items():
                m_dict[f"cvb.{key}"] = value
        if pdf_name in self.pm.paper_dblp_by_path:
            dblp_record = self.pm.paper_dblp_by_path[pdf_name]
            for key, value in dblp_record.items():
                m_dict[f"dblp.{key}"] = value
        return m_dict

    def as_wb_dict(self) -> dict:
        """
        wb create-entity '{"labels":{"en":"a label","fr":"un label"},"descriptions":{"en":"some description","fr":"une description"},"claims":{"P1775":["Q3576110","Q12206942"],"P2002":"bulgroz"}}'
        """
        wb = {
            "labels": {"en": self.title},
            "descriptions": {
                "en": f"scientific paper published in CEUR-WS Volume {self.volume.number}"
            },
            "claims": {
                # P31  :instance of  Q13442814:scholarly article
                "P31": "Q13442814",
                #  P1433: published in
                "P1433": self.volume.wikidataid,
                # P1476:title
                "P1476": {"text": self.title, "language": "en"},
                # P407 :language of work or name  Q1860:English
                "P407": "Q1860",
                #  P953 :full work available at URL
                "P953": self.pdfUrl,
                # P50: author, P1545: series ordinal
                "P50": [],
                # P2093: author name string, P1545: series ordinal
                "P2093": [],
            },
        }
        author_claims = wb["claims"]["P50"]
        author_name_claims = wb["claims"]["P2093"]
        authors = self.getAuthors()
        for index, author in enumerate(authors):
            if not author.wikidata_id:
                author_name_claims.append(
                    {"value": author.name, "qualifiers": {"P1545": f"{index+1}"}}
                )
            else:
                author_claims.append(
                    {"value": author.wikidata_id, "qualifiers": {"P1545": f"{index+1}"}}
                )
        return wb

    def as_wbi_cli_text(self, qid: str) -> str:
        """
        Generates a series of Wikibase CLI command strings to add claims to the entity
        represented by this paper, based on the provided QID.

        Args:
            qid (str): The QID of the Wikibase item to which the claims will be added.

        Returns:
            str: A string containing all the 'wb add-claim' commands separated by newlines.
        """
        # Get the dictionary representation of the paper
        wb_dict = self.as_wb_dict()

        # Initialize an empty list to hold all commands
        cli_commands = []

        # Iterate through each claim to create a separate wb add-claim command
        for prop, value in wb_dict["claims"].items():
            # Handle different structures in claims (e.g., simple vs. complex with qualifiers)
            if isinstance(
                value, list
            ):  # Expecting a list of values (or complex value structures)
                for val in value:
                    # Convert value to a JSON string and escape quotes for command line
                    val_json = json.dumps(val).replace('"', '\\"')
                    cli_commands.append(f'wb add-claim {qid} {prop} "{val_json}"')
            else:  # A single value or simple structure
                # Convert value to a JSON string and escape quotes for command line
                value_json = json.dumps(value).replace('"', '\\"')
                cli_commands.append(f'wb add-claim {qid} {prop} "{value_json}"')

        # Combine all commands into a single string separated by newlines
        cli = "\n".join(cli_commands)
        return cli

    def as_quickstatements(self) -> str:
        """
        return my quickstatements
        """
        m_dict = self.getMergedDict()
        paper_date_str = self.volume.date
        paper_date = datetime.strptime(paper_date_str, "%Y-%m-%d")
        qs_date = f"+{paper_date.isoformat(sep='T',timespec='auto')}Z/11"
        qs = f"""# created by {__file__}
CREATE
# P31  :instance of  Q13442814:scholarly article
LAST|P31|Q13442814
# P1433: published in 
LAST|P1433|{self.volume.wikidataid}
# english label
LAST|Len|"{self.title}"
# english description
LAST|Den|"scientific paper published in CEUR-WS Volume {self.volume.number}"
# P1476:title
LAST|P1476|en:"{self.title}"
# P407 :language of work or name  Q1860:English
LAST|P407|Q1860
# P953 :full work available at URL
LAST|P953|"{self.pdfUrl}"
# P577 :publication date
LAST|P577|{qs_date}
"""
        # @TODO pages ...
        authors = self.getAuthors()
        for index, author in enumerate(authors):
            if not author.wikidata_id:
                qs += f"""# P2093: author name string, P1545: series ordinal
LAST|P2093|"{author.name}"|P1545|"{index+1}"
"""
            else:
                qs += f"""# P50: author, P1545: series ordinal
LAST|P50|{author.wikidata_id}|P1545|"{index+1}"       
"""
            pass
        return qs

    def as_smw_markup(self) -> str:
        """
        return my semantic mediawiki markup

        Returns:
            str: the smw markup for this paper
        """
        m_dict = self.getMergedDict()
        self.authors = m_dict["cvb.authors"]
        if "dblp.dblp_publication_id" in m_dict:
            self.dblpUrl = m_dict["dblp.dblp_publication_id"]
        markup = f"""=Paper=
{{{{Paper
|id={self.id}
|storemode=property
|title={self.title}
|pdfUrl={self.pdfUrl}
|volume=Vol-{self.volume.number}
"""
        for attr in ["authors", "wikidataid", "dblpUrl"]:
            if hasattr(self, attr):
                value = getattr(self, attr)
                if value:
                    markup += f"|{attr}={value}\n"
        markup += f"""}}}}
=={self.title}==
<pdf width="1500px">{self.pdfUrl}</pdf>
<pre>
{self.getText()}
</pre>
        """
        return markup

    def getAuthorIndex(self, name: str, authors: typing.List[str]):
        """
        get the author index
        """
        for i, aname in enumerate(authors):
            if name.lower().startswith(aname.lower()):
                return i
        # if not found put at end
        return len(authors) + 1

    def getAuthors(self) -> typing.List[Scholar]:
        """
        get my authors

        Returns:
            list: a list of Scholars
        """
        m_dict = self.getMergedDict()
        author_names = m_dict["cvb.authors"].split(",")
        if "dblp.authors" in m_dict:
            authors = []
            dblp_author_records = m_dict["dblp.authors"]
            for dblp_author_record in dblp_author_records:
                author = DataClassUtil.dataclass_from_dict(Scholar, dblp_author_record)
                authors.append(author)
                author.index = self.getAuthorIndex(author.label, author_names)
                if author.index < len(author_names):
                    author.name = author_names[author.index]
                else:
                    author.name = author.label
            sorted_authors = sorted(authors, key=lambda author: author.index)
        else:
            sorted_authors = []
            for author_name in author_names:
                scholar = Scholar(dblp_author_id=None, label=author_name)
                scholar.name = author_name
                sorted_authors.append(scholar)
        return sorted_authors

    def getAuthorBar(self):
        """
        show the authors of this paper
        """
        authors = self.getAuthors()
        html = ""
        for author in authors:
            icon_list = [
                {
                    "src": "/static/icons/32px-dblp-icon.png",
                    "title": "dblp",
                    "link": f"{author.dblp_author_id}",
                    "valid": author.dblp_author_id,
                },
                {
                    "src": "/static/icons/32px-ORCID-icon.png",
                    "title": "ORCID",
                    "link": f"https://orcid.org/{author.orcid_id}",
                    "valid": author.orcid_id,
                },
                {
                    "src": "/static/icons/32px-DNB.svg.png",
                    "title": "DNB",
                    "link": f"https://d-nb.info/gnd/{author.gnd_id}",
                    "valid": author.gnd_id,
                },
                {
                    "src": "/static/icons/32px-Scholia_logo.svg.png",
                    "title": "Author@scholia",
                    "link": f"https://scholia.toolforge.org/author/{author.wikidata_id}",
                    "valid": author.wikidata_id,
                },
                {
                    "src": "/static/icons/32px-Wikidata_Query_Service_Favicon_wbg.svg.png",
                    "title": "Author@wikidata",
                    "link": f"https://www.wikidata.org/wiki/{author.wikidata_id}",
                    "valid": author.wikidata_id,
                },
            ]
            soup = BeautifulSoup("<html></html>", "html.parser")
            link_tags = Volume.create_icon_list(soup, icon_list)
            red = (
                not author.wikidata_id
                and not author.dblp_author_id
                and not author.gnd_id
                and not author.orcid_id
            )
            style = "color:red" if red else ""
            html += f"""<span style="{style}">{author.label}"""
            for link_tag in link_tags:
                html += str(link_tag)
            html += "</span>"
            pass
        return html

    def paperLinkParts(self: int, inc: int = 0):
        """
        a relative paper link
        """
        if inc > 0:
            presymbol = "⫸"
            postsymbol = ""
            paper = self.next()
        elif inc < 0:
            presymbol = ""
            postsymbol = "â«·"
            paper = self.prev()
        else:
            presymbol = ""
            postsymbol = ""
            paper = self
        href = None
        text = None
        if paper:
            href = f"/{paper.id}.html"
            text = f"{presymbol}{paper.id}{postsymbol}"
        return href, text

    def paperScrollLinks(self) -> str:
        """
        get the paper scroll links
        """
        scroll_links = ""
        for inc in [-1, 0, 1]:
            href, text = self.paperLinkParts(inc)
            if href:
                scroll_links += f"""<a href="{href}">{text}</a>"""
        return scroll_links

    def prev(self) -> "Paper":
        """
        get the previous paper in this volume
        """
        return self.next(-1)

    def next(self, inc: int = 1) -> "Paper":
        """
        get the next paper in this volume with the given increment

        Args:
            inc(int): the increment +1 = next, -1 = prev
        """
        vol = self.volume
        paper = None
        if vol:
            next_index = self.paper_index + inc
            if next_index >= 0 and next_index < len(vol.papers):
                paper = vol.papers[next_index]
        return paper

    def getIconBar(self, soup):
        """
        get my icon bar

        Parameters:
            soup: The BeautifulSoup object to use for creating new tags.
        """
        pdf_name = self.pdfUrl.replace("https://ceur-ws.org/", "")
        pdf_name = pdf_name.replace(".pdf", "")
        # create a list of icons to add to the div
        icon_list = [
            {
                "src": "/static/icons/32px-text-icon.png",
                "title": "plain text",
                "link": f"/{pdf_name}.txt",
                "valid": self.getContentPathByPostfix(".txt"),
            },
            {
                "src": "/static/icons/32px-PDF_icon.svg.png",
                "title": "original pdf",
                "link": f"/{pdf_name}.pdf",
                "valid": self.getContentPathByPostfix(".pdf"),
            },
            {
                "src": "/static/icons/32px-Cermine-Icon.png",
                "title": "Cermine metadata",
                "link": f"/{pdf_name}.cermine",
                "valid": self.getContentPathByPostfix(".cermine"),
            },
            {
                "src": "/static/icons/32px-GROBID-icon.png",
                "title": "GROBID metadata",
                "link": f"/{pdf_name}.grobid",
                "valid": self.getContentPathByPostfix(".grobid"),
            },
            {
                "src": "/static/icons/32px-QuickStatements-icon.png",
                "title": "Quickstatements",
                "link": f"/{pdf_name}.qs",
                "valid": True,  # @TODO - add check for existing wikidata entry
            },
            {
                "src": "/static/icons/32px-SMW-icon.png",
                "title": "SMW markup",
                "link": f"/{pdf_name}.smw",
                "valid": True,
            },
            {
                "src": "/static/icons/32px-wbjson-icon.png",
                "title": "wikibase CLI JSON metadata",
                "link": f"/{pdf_name}.wbjson",
                "valid": True,
            },
            {
                "src": "/static/icons/32px-Wikibase_logo.svg.png",
                "title": "wikibase CLI",
                "link": f"/{pdf_name}.wbcli",
                "valid": True,
            },
            {
                "src": "/static/icons/32px-JSON_vector_logo.svg.png",
                "title": "JSON metadata",
                "link": f"/{pdf_name}.json",
                "valid": True,
            },
            {
                "src": "/static/icons/32px-YAML_Logo.svg.png",
                "title": "YAML metadata",
                "link": f"/{pdf_name}.yaml",
                "valid": True,
            },
        ]
        icon_tag = Volume.create_icon_bar(soup, icon_list=icon_list)
        return icon_tag

    def asHtml(self):
        """
        return an html response for this paper
        """
        soup = BeautifulSoup("<html></html>", "html.parser")
        icon_bar = self.getIconBar(soup)
        author_bar = self.getAuthorBar()
        content = f"""<!DOCTYPE html>
<html lang="en">
<head>
<meta http-equiv="Content-type" content="text/html;charset=utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<link rel="stylesheet" type="text/css" href="/static/ceur-ws.css">
<title>{self.id} - {self.title}</title>
</head>
<body>
<table style="border: 0; border-spacing: 0; border-collapse: collapse; width: 95%">
<tbody><tr>
<td style="text-align: left; vertical-align: middle">
<a href="http://ceur-ws.org/"><div id="CEURWSLOGO"></div></a>
</td>
<td style="text-align: right; vertical-align: middle">
<div style="float:left" id="CEURCCBY"></div>
{Volume.volLink(self.volume.number,-1)}
<span class="CEURVOLNR">{Volume.volLink(self.volume.number)}</span>
{Volume.volLink(self.volume.number,+1)}<br>
<span class="CEURURN">urn:nbn:de:0074-{self.volume.number}-0</span>
<p class="unobtrusive copyright" style="text-align: justify">Copyright &copy; {self.volume.date[:4]} for
the individual papers by the papers' authors. 
Copyright &copy; <span class="CEURPUBYEAR">{self.volume.date[:4]}</span> for the volume
as a collection by its editors.
This volume and its papers are published under the
Creative Commons License Attribution 4.0 International
<A HREF="https://creativecommons.org/licenses/by/4.0/">(<span class="CEURLIC">CC BY 4.0</span>)</A>.</p>
</td>
</tr>
</tbody></table>
{str(icon_bar)}
<hr/>
{self.paperScrollLinks()}
<hr/>
{str(author_bar)}
<hr/>
<h1>{self.title}<h1>
<embed src="{self.pdfUrl}" style="width:100vw;height:100vh" type="application/pdf">
<body>
</body>
        """
        return content

asHtml()

return an html response for this paper

Source code in ceurspt/ceurws.py 
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
    def asHtml(self):
        """
        return an html response for this paper
        """
        soup = BeautifulSoup("<html></html>", "html.parser")
        icon_bar = self.getIconBar(soup)
        author_bar = self.getAuthorBar()
        content = f"""<!DOCTYPE html>
<html lang="en">
<head>
<meta http-equiv="Content-type" content="text/html;charset=utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<link rel="stylesheet" type="text/css" href="/static/ceur-ws.css">
<title>{self.id} - {self.title}</title>
</head>
<body>
<table style="border: 0; border-spacing: 0; border-collapse: collapse; width: 95%">
<tbody><tr>
<td style="text-align: left; vertical-align: middle">
<a href="http://ceur-ws.org/"><div id="CEURWSLOGO"></div></a>
</td>
<td style="text-align: right; vertical-align: middle">
<div style="float:left" id="CEURCCBY"></div>
{Volume.volLink(self.volume.number,-1)}
<span class="CEURVOLNR">{Volume.volLink(self.volume.number)}</span>
{Volume.volLink(self.volume.number,+1)}<br>
<span class="CEURURN">urn:nbn:de:0074-{self.volume.number}-0</span>
<p class="unobtrusive copyright" style="text-align: justify">Copyright &copy; {self.volume.date[:4]} for
the individual papers by the papers' authors. 
Copyright &copy; <span class="CEURPUBYEAR">{self.volume.date[:4]}</span> for the volume
as a collection by its editors.
This volume and its papers are published under the
Creative Commons License Attribution 4.0 International
<A HREF="https://creativecommons.org/licenses/by/4.0/">(<span class="CEURLIC">CC BY 4.0</span>)</A>.</p>
</td>
</tr>
</tbody></table>
{str(icon_bar)}
<hr/>
{self.paperScrollLinks()}
<hr/>
{str(author_bar)}
<hr/>
<h1>{self.title}<h1>
<embed src="{self.pdfUrl}" style="width:100vw;height:100vh" type="application/pdf">
<body>
</body>
        """
        return content

as_quickstatements()

return my quickstatements

Source code in ceurspt/ceurws.py 
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
    def as_quickstatements(self) -> str:
        """
        return my quickstatements
        """
        m_dict = self.getMergedDict()
        paper_date_str = self.volume.date
        paper_date = datetime.strptime(paper_date_str, "%Y-%m-%d")
        qs_date = f"+{paper_date.isoformat(sep='T',timespec='auto')}Z/11"
        qs = f"""# created by {__file__}
CREATE
# P31  :instance of  Q13442814:scholarly article
LAST|P31|Q13442814
# P1433: published in 
LAST|P1433|{self.volume.wikidataid}
# english label
LAST|Len|"{self.title}"
# english description
LAST|Den|"scientific paper published in CEUR-WS Volume {self.volume.number}"
# P1476:title
LAST|P1476|en:"{self.title}"
# P407 :language of work or name  Q1860:English
LAST|P407|Q1860
# P953 :full work available at URL
LAST|P953|"{self.pdfUrl}"
# P577 :publication date
LAST|P577|{qs_date}
"""
        # @TODO pages ...
        authors = self.getAuthors()
        for index, author in enumerate(authors):
            if not author.wikidata_id:
                qs += f"""# P2093: author name string, P1545: series ordinal
LAST|P2093|"{author.name}"|P1545|"{index+1}"
"""
            else:
                qs += f"""# P50: author, P1545: series ordinal
LAST|P50|{author.wikidata_id}|P1545|"{index+1}"       
"""
            pass
        return qs

as_smw_markup()

return my semantic mediawiki markup

Returns:

Name Type Description
str str

the smw markup for this paper
Source code in ceurspt/ceurws.py 
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
    def as_smw_markup(self) -> str:
        """
        return my semantic mediawiki markup

        Returns:
            str: the smw markup for this paper
        """
        m_dict = self.getMergedDict()
        self.authors = m_dict["cvb.authors"]
        if "dblp.dblp_publication_id" in m_dict:
            self.dblpUrl = m_dict["dblp.dblp_publication_id"]
        markup = f"""=Paper=
{{{{Paper
|id={self.id}
|storemode=property
|title={self.title}
|pdfUrl={self.pdfUrl}
|volume=Vol-{self.volume.number}
"""
        for attr in ["authors", "wikidataid", "dblpUrl"]:
            if hasattr(self, attr):
                value = getattr(self, attr)
                if value:
                    markup += f"|{attr}={value}\n"
        markup += f"""}}}}
=={self.title}==
<pdf width="1500px">{self.pdfUrl}</pdf>
<pre>
{self.getText()}
</pre>
        """
        return markup

as_wb_dict()

wb create-entity '{"labels":{"en":"a label","fr":"un label"},"descriptions":{"en":"some description","fr":"une description"},"claims":{"P1775":["Q3576110","Q12206942"],"P2002":"bulgroz"}}'

Source code in ceurspt/ceurws.py 
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
def as_wb_dict(self) -> dict:
    """
    wb create-entity '{"labels":{"en":"a label","fr":"un label"},"descriptions":{"en":"some description","fr":"une description"},"claims":{"P1775":["Q3576110","Q12206942"],"P2002":"bulgroz"}}'
    """
    wb = {
        "labels": {"en": self.title},
        "descriptions": {
            "en": f"scientific paper published in CEUR-WS Volume {self.volume.number}"
        },
        "claims": {
            # P31  :instance of  Q13442814:scholarly article
            "P31": "Q13442814",
            #  P1433: published in
            "P1433": self.volume.wikidataid,
            # P1476:title
            "P1476": {"text": self.title, "language": "en"},
            # P407 :language of work or name  Q1860:English
            "P407": "Q1860",
            #  P953 :full work available at URL
            "P953": self.pdfUrl,
            # P50: author, P1545: series ordinal
            "P50": [],
            # P2093: author name string, P1545: series ordinal
            "P2093": [],
        },
    }
    author_claims = wb["claims"]["P50"]
    author_name_claims = wb["claims"]["P2093"]
    authors = self.getAuthors()
    for index, author in enumerate(authors):
        if not author.wikidata_id:
            author_name_claims.append(
                {"value": author.name, "qualifiers": {"P1545": f"{index+1}"}}
            )
        else:
            author_claims.append(
                {"value": author.wikidata_id, "qualifiers": {"P1545": f"{index+1}"}}
            )
    return wb

as_wbi_cli_text(qid)

Generates a series of Wikibase CLI command strings to add claims to the entity represented by this paper, based on the provided QID.

Parameters:

Name Type Description Default
qid str

The QID of the Wikibase item to which the claims will be added.

 required

Returns:

Name Type Description
str str

A string containing all the 'wb add-claim' commands separated by newlines.
Source code in ceurspt/ceurws.py 
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
def as_wbi_cli_text(self, qid: str) -> str:
    """
    Generates a series of Wikibase CLI command strings to add claims to the entity
    represented by this paper, based on the provided QID.

    Args:
        qid (str): The QID of the Wikibase item to which the claims will be added.

    Returns:
        str: A string containing all the 'wb add-claim' commands separated by newlines.
    """
    # Get the dictionary representation of the paper
    wb_dict = self.as_wb_dict()

    # Initialize an empty list to hold all commands
    cli_commands = []

    # Iterate through each claim to create a separate wb add-claim command
    for prop, value in wb_dict["claims"].items():
        # Handle different structures in claims (e.g., simple vs. complex with qualifiers)
        if isinstance(
            value, list
        ):  # Expecting a list of values (or complex value structures)
            for val in value:
                # Convert value to a JSON string and escape quotes for command line
                val_json = json.dumps(val).replace('"', '\\"')
                cli_commands.append(f'wb add-claim {qid} {prop} "{val_json}"')
        else:  # A single value or simple structure
            # Convert value to a JSON string and escape quotes for command line
            value_json = json.dumps(value).replace('"', '\\"')
            cli_commands.append(f'wb add-claim {qid} {prop} "{value_json}"')

    # Combine all commands into a single string separated by newlines
    cli = "\n".join(cli_commands)
    return cli

getAuthorBar()

show the authors of this paper

Source code in ceurspt/ceurws.py 
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
def getAuthorBar(self):
    """
    show the authors of this paper
    """
    authors = self.getAuthors()
    html = ""
    for author in authors:
        icon_list = [
            {
                "src": "/static/icons/32px-dblp-icon.png",
                "title": "dblp",
                "link": f"{author.dblp_author_id}",
                "valid": author.dblp_author_id,
            },
            {
                "src": "/static/icons/32px-ORCID-icon.png",
                "title": "ORCID",
                "link": f"https://orcid.org/{author.orcid_id}",
                "valid": author.orcid_id,
            },
            {
                "src": "/static/icons/32px-DNB.svg.png",
                "title": "DNB",
                "link": f"https://d-nb.info/gnd/{author.gnd_id}",
                "valid": author.gnd_id,
            },
            {
                "src": "/static/icons/32px-Scholia_logo.svg.png",
                "title": "Author@scholia",
                "link": f"https://scholia.toolforge.org/author/{author.wikidata_id}",
                "valid": author.wikidata_id,
            },
            {
                "src": "/static/icons/32px-Wikidata_Query_Service_Favicon_wbg.svg.png",
                "title": "Author@wikidata",
                "link": f"https://www.wikidata.org/wiki/{author.wikidata_id}",
                "valid": author.wikidata_id,
            },
        ]
        soup = BeautifulSoup("<html></html>", "html.parser")
        link_tags = Volume.create_icon_list(soup, icon_list)
        red = (
            not author.wikidata_id
            and not author.dblp_author_id
            and not author.gnd_id
            and not author.orcid_id
        )
        style = "color:red" if red else ""
        html += f"""<span style="{style}">{author.label}"""
        for link_tag in link_tags:
            html += str(link_tag)
        html += "</span>"
        pass
    return html

getAuthorIndex(name, authors)

get the author index

Source code in ceurspt/ceurws.py 
274
275
276
277
278
279
280
281
282
def getAuthorIndex(self, name: str, authors: typing.List[str]):
    """
    get the author index
    """
    for i, aname in enumerate(authors):
        if name.lower().startswith(aname.lower()):
            return i
    # if not found put at end
    return len(authors) + 1

getAuthors()

get my authors

Returns:

Name Type Description
list List[Scholar]

a list of Scholars
Source code in ceurspt/ceurws.py 
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
def getAuthors(self) -> typing.List[Scholar]:
    """
    get my authors

    Returns:
        list: a list of Scholars
    """
    m_dict = self.getMergedDict()
    author_names = m_dict["cvb.authors"].split(",")
    if "dblp.authors" in m_dict:
        authors = []
        dblp_author_records = m_dict["dblp.authors"]
        for dblp_author_record in dblp_author_records:
            author = DataClassUtil.dataclass_from_dict(Scholar, dblp_author_record)
            authors.append(author)
            author.index = self.getAuthorIndex(author.label, author_names)
            if author.index < len(author_names):
                author.name = author_names[author.index]
            else:
                author.name = author.label
        sorted_authors = sorted(authors, key=lambda author: author.index)
    else:
        sorted_authors = []
        for author_name in author_names:
            scholar = Scholar(dblp_author_id=None, label=author_name)
            scholar.name = author_name
            sorted_authors.append(scholar)
    return sorted_authors

getBasePath()

get the base path to my files

Source code in ceurspt/ceurws.py 
38
39
40
41
42
43
44
45
46
47
48
def getBasePath(self) -> Optional[str]:
    """
    get the base path to my files
    """
    if self.pdfUrl:
        base_path = self.pdfUrl.replace("https://ceur-ws.org/", "")
        base_path = base_path.replace(".pdf", "")
        base_path = f"{self.volume.vm.base_path}/{base_path}"
        if os.path.isfile(f"{base_path}.pdf"):
            return base_path
    return None

getContentByPostfix(postfix)

get the content for the given postfix

Parameters:

Name Type Description Default
postfix(str)

the postfix to read

 required

Returns:

Name Type Description
str str

the context
Source code in ceurspt/ceurws.py 
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
def getContentByPostfix(self, postfix: str) -> str:
    """
    get the content for the given postfix

    Args:
        postfix(str): the postfix to read

    Returns:
        str: the context
    """
    text_path = self.getContentPathByPostfix(postfix)
    content = None
    if text_path:
        with open(text_path, "r") as text_file:
            content = text_file.read()
    return content

getContentPathByPostfix(postfix)

get the content path for the given postfix

Parameters:

Name Type Description Default
postfix(str)

the postfix to read

 required

Returns:

Name Type Description
str

the context path
Source code in ceurspt/ceurws.py 
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
def getContentPathByPostfix(self, postfix: str):
    """
    get the content path for the given postfix

    Args:
        postfix(str): the postfix to read

    Returns:
        str: the context path
    """
    base_path = self.getBasePath()
    if base_path is None:
        return None
    text_path = f"{base_path}{postfix}"
    if os.path.isfile(text_path):
        return text_path
    else:
        return None

getIconBar(soup)

get my icon bar

Parameters:

Name Type Description Default
soup

The BeautifulSoup object to use for creating new tags.

 required
Source code in ceurspt/ceurws.py 
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
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
def getIconBar(self, soup):
    """
    get my icon bar

    Parameters:
        soup: The BeautifulSoup object to use for creating new tags.
    """
    pdf_name = self.pdfUrl.replace("https://ceur-ws.org/", "")
    pdf_name = pdf_name.replace(".pdf", "")
    # create a list of icons to add to the div
    icon_list = [
        {
            "src": "/static/icons/32px-text-icon.png",
            "title": "plain text",
            "link": f"/{pdf_name}.txt",
            "valid": self.getContentPathByPostfix(".txt"),
        },
        {
            "src": "/static/icons/32px-PDF_icon.svg.png",
            "title": "original pdf",
            "link": f"/{pdf_name}.pdf",
            "valid": self.getContentPathByPostfix(".pdf"),
        },
        {
            "src": "/static/icons/32px-Cermine-Icon.png",
            "title": "Cermine metadata",
            "link": f"/{pdf_name}.cermine",
            "valid": self.getContentPathByPostfix(".cermine"),
        },
        {
            "src": "/static/icons/32px-GROBID-icon.png",
            "title": "GROBID metadata",
            "link": f"/{pdf_name}.grobid",
            "valid": self.getContentPathByPostfix(".grobid"),
        },
        {
            "src": "/static/icons/32px-QuickStatements-icon.png",
            "title": "Quickstatements",
            "link": f"/{pdf_name}.qs",
            "valid": True,  # @TODO - add check for existing wikidata entry
        },
        {
            "src": "/static/icons/32px-SMW-icon.png",
            "title": "SMW markup",
            "link": f"/{pdf_name}.smw",
            "valid": True,
        },
        {
            "src": "/static/icons/32px-wbjson-icon.png",
            "title": "wikibase CLI JSON metadata",
            "link": f"/{pdf_name}.wbjson",
            "valid": True,
        },
        {
            "src": "/static/icons/32px-Wikibase_logo.svg.png",
            "title": "wikibase CLI",
            "link": f"/{pdf_name}.wbcli",
            "valid": True,
        },
        {
            "src": "/static/icons/32px-JSON_vector_logo.svg.png",
            "title": "JSON metadata",
            "link": f"/{pdf_name}.json",
            "valid": True,
        },
        {
            "src": "/static/icons/32px-YAML_Logo.svg.png",
            "title": "YAML metadata",
            "link": f"/{pdf_name}.yaml",
            "valid": True,
        },
    ]
    icon_tag = Volume.create_icon_bar(soup, icon_list=icon_list)
    return icon_tag

getMergedDict()

get the merged dict for this paper

Source code in ceurspt/ceurws.py 
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
def getMergedDict(self) -> dict:
    """
    get the merged dict for this paper
    """
    my_dict = dataclasses.asdict(self)
    m_dict = {
        "version.version": Version.version,
        "version.cm_url": Version.cm_url,
        "spt.html_url": f"/{self.id}.html",
    }
    for key, value in my_dict.items():
        m_dict[f"spt.{key}"] = value
    pdf_name = self.pdfUrl.replace("https://ceur-ws.org/", "")
    if pdf_name in self.pm.paper_records_by_path:
        pdf_record = self.pm.paper_records_by_path[pdf_name]
        for key, value in pdf_record.items():
            m_dict[f"cvb.{key}"] = value
    if pdf_name in self.pm.paper_dblp_by_path:
        dblp_record = self.pm.paper_dblp_by_path[pdf_name]
        for key, value in dblp_record.items():
            m_dict[f"dblp.{key}"] = value
    return m_dict

getPdf()

get the PDF file for this paper

Source code in ceurspt/ceurws.py 
93
94
95
96
97
98
99
def getPdf(self):
    """
    get the PDF file for this paper
    """
    base_path = self.getBasePath()
    pdf = f"{base_path}.pdf"
    return pdf

getText()

get the plain text content of this paper

Source code in ceurspt/ceurws.py 
86
87
88
89
90
91
def getText(self) -> str:
    """
    get the plain text content of this paper
    """
    text = self.getContentByPostfix("-content.txt")
    return text

next(inc=1)

get the next paper in this volume with the given increment

Parameters:

Name Type Description Default
inc(int)

the increment +1 = next, -1 = prev

 required
Source code in ceurspt/ceurws.py 
408
409
410
411
412
413
414
415
416
417
418
419
420
421
def next(self, inc: int = 1) -> "Paper":
    """
    get the next paper in this volume with the given increment

    Args:
        inc(int): the increment +1 = next, -1 = prev
    """
    vol = self.volume
    paper = None
    if vol:
        next_index = self.paper_index + inc
        if next_index >= 0 and next_index < len(vol.papers):
            paper = vol.papers[next_index]
    return paper

paperLinkParts(inc=0)

a relative paper link

Source code in ceurspt/ceurws.py 
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
def paperLinkParts(self: int, inc: int = 0):
    """
    a relative paper link
    """
    if inc > 0:
        presymbol = "⫸"
        postsymbol = ""
        paper = self.next()
    elif inc < 0:
        presymbol = ""
        postsymbol = "â«·"
        paper = self.prev()
    else:
        presymbol = ""
        postsymbol = ""
        paper = self
    href = None
    text = None
    if paper:
        href = f"/{paper.id}.html"
        text = f"{presymbol}{paper.id}{postsymbol}"
    return href, text

get the paper scroll links

Source code in ceurspt/ceurws.py 
391
392
393
394
395
396
397
398
399
400
def paperScrollLinks(self) -> str:
    """
    get the paper scroll links
    """
    scroll_links = ""
    for inc in [-1, 0, 1]:
        href, text = self.paperLinkParts(inc)
        if href:
            scroll_links += f"""<a href="{href}">{text}</a>"""
    return scroll_links

prev()

get the previous paper in this volume

Source code in ceurspt/ceurws.py 
402
403
404
405
406
def prev(self) -> "Paper":
    """
    get the previous paper in this volume
    """
    return self.next(-1)

PaperManager

Bases: JsonCacheManager

manage all papers

Source code in ceurspt/ceurws.py 
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
class PaperManager(JsonCacheManager):
    """
    manage all papers
    """

    def __init__(self, base_url: str):
        """
        constructor

        Args:
            base_url(str): the url of the RESTFul metadata service
        """
        JsonCacheManager.__init__(self, base_url)
        self.papers_by_id: Dict[str, Paper] = {}
        self.papers_by_path: Dict[str, Paper] = {}
        self.paper_records_by_path: Dict[str, dict] = {}
        self.paper_dblp_by_path: Dict[str, dict] = {}

    def getPaper(self, number: int, pdf_name: str):
        """
        get the paper with the given number and pdf name

        Args:
            number(int): the number of the volume the paper is part of
            pdf_name(str): the pdf name of the paper

        Returns:
            Paper: the paper or None if the paper is not found
        """
        pdf_path = f"Vol-{number}/{pdf_name}.pdf"
        paper = None
        if pdf_path in self.papers_by_path:
            paper = self.papers_by_path[pdf_path]
            paper.pm = self
        return paper

    def get_volume_papers(self, number: int) -> List[Paper]:
        """
        Get all papers of given volume number
        Args:
            number(int): the number of the volume the papers are part of
        Returns:
            list of papers
        """
        volume_papers = [
            paper
            for pdf_path, paper in self.papers_by_path.items()
            if pdf_path.startswith(f"Vol-{number}/")
        ]
        return volume_papers

    def getPapers(self, vm: VolumeManager, verbose: bool = False):
        """
        get all papers

        Args:
            vm: VolumeManager
            verbose(bool): if True show verbose loading information
        """
        profiler = Profiler("Loading papers ...", profile=verbose)
        paper_lod = self.load_lod("papers")
        msg = f"{len(paper_lod)} papers"
        profiler.time(msg)
        profiler = Profiler("Loading dblp paper metadata ...", profile=verbose)
        paper_dblp_lod = self.load_lod("papers_dblp")
        msg = f"{len(paper_dblp_lod)} dblp indexed papers"
        profiler.time(msg)
        profiler = Profiler("Linking papers and volumes...", profile=verbose)
        self.papers_by_id = {}
        self.paper_records_by_path = {}
        self.papers_by_path = {}
        for _index, paper_record in enumerate(paper_lod):
            pdf_name = paper_record["pdf_name"]
            volume_number = paper_record["vol_number"]
            volume = vm.getVolume(volume_number)
            # pdf_url=f"https://ceur-ws.org/Vol-{volume_number}/{pdf_name}"
            pdf_path = f"Vol-{volume_number}/{pdf_name}"
            pdf_url = f"https://ceur-ws.org/{pdf_path}"
            try:
                paper = Paper(
                    id=paper_record["id"],
                    title=paper_record["title"],
                    # authors=paper_record["authors"],
                    pdfUrl=pdf_url,
                    volume=volume,
                )
                paper.pm = self
                if volume:
                    volume.addPaper(paper)
                self.papers_by_id[paper_record["id"]] = paper
                self.papers_by_path[pdf_path] = paper
                self.paper_records_by_path[pdf_path] = paper_record
            except Exception as ex:
                print(
                    f"handling of Paper for pdfUrl '{pdf_url}' failed with {str(ex)}",
                    flush=True,
                )
        self.paper_dblp_by_path = {}
        for _index, dblp_record in enumerate(paper_dblp_lod):
            pdf_id = dblp_record["pdf_id"]
            self.paper_dblp_by_path[f"{pdf_id}.pdf"] = dblp_record
        msg = f"{len(self.papers_by_path)} papers linked to volumes"
        profiler.time(msg)

__init__(base_url)

constructor

Parameters:

Name Type Description Default
base_url(str)

the url of the RESTFul metadata service

 required
Source code in ceurspt/ceurws.py 
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
def __init__(self, base_url: str):
    """
    constructor

    Args:
        base_url(str): the url of the RESTFul metadata service
    """
    JsonCacheManager.__init__(self, base_url)
    self.papers_by_id: Dict[str, Paper] = {}
    self.papers_by_path: Dict[str, Paper] = {}
    self.paper_records_by_path: Dict[str, dict] = {}
    self.paper_dblp_by_path: Dict[str, dict] = {}

getPaper(number, pdf_name)

get the paper with the given number and pdf name

Parameters:

Name Type Description Default
number(int)

the number of the volume the paper is part of

 required
pdf_name(str)

the pdf name of the paper

 required

Returns:

Name Type Description
Paper

the paper or None if the paper is not found
Source code in ceurspt/ceurws.py 
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
def getPaper(self, number: int, pdf_name: str):
    """
    get the paper with the given number and pdf name

    Args:
        number(int): the number of the volume the paper is part of
        pdf_name(str): the pdf name of the paper

    Returns:
        Paper: the paper or None if the paper is not found
    """
    pdf_path = f"Vol-{number}/{pdf_name}.pdf"
    paper = None
    if pdf_path in self.papers_by_path:
        paper = self.papers_by_path[pdf_path]
        paper.pm = self
    return paper

getPapers(vm, verbose=False)

get all papers

Parameters:

Name Type Description Default
vm VolumeManager

VolumeManager

 required
verbose(bool)

if True show verbose loading information

 required
Source code in ceurspt/ceurws.py 
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
def getPapers(self, vm: VolumeManager, verbose: bool = False):
    """
    get all papers

    Args:
        vm: VolumeManager
        verbose(bool): if True show verbose loading information
    """
    profiler = Profiler("Loading papers ...", profile=verbose)
    paper_lod = self.load_lod("papers")
    msg = f"{len(paper_lod)} papers"
    profiler.time(msg)
    profiler = Profiler("Loading dblp paper metadata ...", profile=verbose)
    paper_dblp_lod = self.load_lod("papers_dblp")
    msg = f"{len(paper_dblp_lod)} dblp indexed papers"
    profiler.time(msg)
    profiler = Profiler("Linking papers and volumes...", profile=verbose)
    self.papers_by_id = {}
    self.paper_records_by_path = {}
    self.papers_by_path = {}
    for _index, paper_record in enumerate(paper_lod):
        pdf_name = paper_record["pdf_name"]
        volume_number = paper_record["vol_number"]
        volume = vm.getVolume(volume_number)
        # pdf_url=f"https://ceur-ws.org/Vol-{volume_number}/{pdf_name}"
        pdf_path = f"Vol-{volume_number}/{pdf_name}"
        pdf_url = f"https://ceur-ws.org/{pdf_path}"
        try:
            paper = Paper(
                id=paper_record["id"],
                title=paper_record["title"],
                # authors=paper_record["authors"],
                pdfUrl=pdf_url,
                volume=volume,
            )
            paper.pm = self
            if volume:
                volume.addPaper(paper)
            self.papers_by_id[paper_record["id"]] = paper
            self.papers_by_path[pdf_path] = paper
            self.paper_records_by_path[pdf_path] = paper_record
        except Exception as ex:
            print(
                f"handling of Paper for pdfUrl '{pdf_url}' failed with {str(ex)}",
                flush=True,
            )
    self.paper_dblp_by_path = {}
    for _index, dblp_record in enumerate(paper_dblp_lod):
        pdf_id = dblp_record["pdf_id"]
        self.paper_dblp_by_path[f"{pdf_id}.pdf"] = dblp_record
    msg = f"{len(self.papers_by_path)} papers linked to volumes"
    profiler.time(msg)

get_volume_papers(number)

Get all papers of given volume number Args: number(int): the number of the volume the papers are part of Returns: list of papers

Source code in ceurspt/ceurws.py 
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
def get_volume_papers(self, number: int) -> List[Paper]:
    """
    Get all papers of given volume number
    Args:
        number(int): the number of the volume the papers are part of
    Returns:
        list of papers
    """
    volume_papers = [
        paper
        for pdf_path, paper in self.papers_by_path.items()
        if pdf_path.startswith(f"Vol-{number}/")
    ]
    return volume_papers

Scholar dataclass

Bases: DblpScholar

a scholar

Source code in ceurspt/ceurws.py 
27
28
29
30
class Scholar(ceurspt.models.dblp.DblpScholar):
    """
    a scholar
    """

Volume

Bases: Volume

a CEUR-WS Volume with it's behavior

Source code in ceurspt/ceurws.py 
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
class Volume(ceurspt.ceurws_base.Volume):
    """
    a CEUR-WS Volume with it's behavior
    """

    def __init__(self, **kwargs):
        ceurspt.ceurws_base.Volume.__init__(self, **kwargs)
        self.papers = []

    def getMergedDict(self) -> dict:
        """
        get my merged dict

        Returns:
            dict
        """
        my_dict = dataclasses.asdict(self)
        m_dict = {
            "version.version": Version.version,
            "version.cm_url": Version.cm_url,
            "spt.html_url": f"/Vol-{self.number}.html",
        }
        for key, value in my_dict.items():
            m_dict[f"spt.{key}"] = value
        volrecord = self.vm.getVolumeRecord(self.number)
        for key, value in volrecord.items():
            if "." in key:
                m_dict[f"{key}"] = value
            else:
                m_dict[f"cvb.{key}"] = value
        return m_dict

    @classmethod
    def volLinkParts(cls, number: int, inc: int = 0):
        """
        a relative volume link
        """
        if inc > 0:
            presymbol = "⫸"
            postsymbol = ""
        elif inc < 0:
            presymbol = ""
            postsymbol = "â«·"
        else:
            presymbol = ""
            postsymbol = ""
        href = f"/Vol-{number+inc}.html"
        text = f"{presymbol}Vol-{number+inc}{postsymbol}"
        return href, text

    @classmethod
    def volLink(cls, number: int, inc: int = 0) -> str:
        """
        get a relative volume link

        Args:
            number(int): the volume number
            inc(int): the relative increment

        Returns(str):
            a relative volume link
        """
        href, text = cls.volLinkParts(number, inc)
        if number > 0:
            link = f"""<a href="{href}">{text}</a>"""
        else:
            link = ""
        return link

    @classmethod
    def volLink_soup_tag(cls, soup, number: int, inc: int = 0) -> str:
        """
        get a relative volume link as a soup tag

        Args:
            soup(BeautifulSoup): the soup
            number(int): the volume number
            inc(int): the relative increment

        Returns(str):
            a relative volume link
        """
        href, text = cls.volLinkParts(number, inc)
        link = soup.new_tag("a", href=href)
        link.string = text
        return link

    @classmethod
    def create_icon_list(
        cls, soup: BeautifulSoup, icon_list: typing.List[typing.Dict[str, str]]
    ) -> typing.List["Tag"]:
        """
        create a list of icons

        Args:
            soup: The BeautifulSoup object to use for creating new tags.
            icon_list: The list of icons to add to the <div> tag. Each icon is represented as a
                dictionary with the following keys:
                    - src (str): The URL of the icon image file.
                    - title (str): The title text to use as a tooltip for the icon.
                    - link (str): The URL to link to when the icon is clicked.

        Returns:
            a list of link_tags
        """
        link_tags = []
        # iterate over the icon list and create a new tag for each icon
        for icon_data in icon_list:
            # create a new a tag for the link
            link_tag = soup.new_tag("a")
            link_tag["href"] = icon_data["link"]
            # open link in new tab
            link_tag["target"] = "_blank"
            if not icon_data["valid"]:
                link_tag["style"] = "filter: grayscale(1);"

            # create a new img tag for the icon
            icon_tag = soup.new_tag("img")

            # add the icon attributes to the img tag
            icon_tag["src"] = icon_data["src"]
            icon_tag["title"] = icon_data["title"]

            # append the icon tag to the link tag
            link_tag.append(icon_tag)
            link_tags.append(link_tag)
        return link_tags

    @classmethod
    def create_icon_bar(
        cls,
        soup: BeautifulSoup,
        icon_list: typing.List[typing.Dict[str, str]],
        class_name: str = "icon_list",
    ) -> "Tag":
        """
        Creates a new <div> tag with the specified class name and list of icons.

        Args:
            soup: The BeautifulSoup object to use for creating new tags.
            icon_list: The list of icons to add to the <div> tag. Each icon is represented as a
                dictionary with the following keys:
                    - src (str): The URL of the icon image file.
                    - title (str): The title text to use as a tooltip for the icon.
                    - link (str): The URL to link to when the icon is clicked.
            class_name: The name of the CSS class to apply to the <div> tag.

        Returns:
            Tag: The new <div> tag with the specified class name and list of icons.
        """

        # create a new div tag
        div_tag = soup.new_tag("div")

        div_tag.append(soup.new_tag("hr"))

        # add the specified class name to the div tag
        div_tag["class"] = [class_name]

        for link_tag in cls.create_icon_list(soup, icon_list):
            # append the link tag to the div tag
            div_tag.append(link_tag)

        # return the div tag
        return div_tag

    def getIconBar(self, soup):
        """
        get my icon bar

        Parameters:
            soup: The BeautifulSoup object to use for creating new tags.
        """
        volume_record = self.vm.getVolumeRecord(self.number)
        for wd_key, attr in [
            ("wd.event", "wd_event"),
            ("wd.eventSeries", "wd_event_series"),
        ]:
            value = None
            if wd_key in volume_record:
                value = volume_record[wd_key]
                if value:
                    value = value.replace("http://www.wikidata.org/entity/", "")
            setattr(self, attr, value)
        # create a list of icons to add to the div
        icon_list = [
            {
                "src": "/static/icons/32px-dblp-icon.png",
                "title": "dblp",
                "link": f"https://dblp.org/rec/{self.dblp}",
                "valid": self.dblp,
            },
            {
                "src": "/static/icons/32px-DNB.svg.png",
                "title": "k10plus/DNB",
                "link": f"https://opac.k10plus.de/DB=2.299/PPNSET?PPN={self.k10plus}",
                "valid": self.k10plus,
            },
            {
                "src": "/static/icons/32px-Scholia_logo.svg.png",
                "title": "Proceedings@scholia",
                "link": f"https://scholia.toolforge.org/venue/{self.wikidataid}",
                "valid": self.wikidataid,
            },
            {
                "src": "/static/icons/32px-EventIcon.png",
                "title": "Event@scholia",
                "link": f"https://scholia.toolforge.org/event/{self.wd_event}",
                "valid": self.wd_event,
            },
            {
                "src": "/static/icons/32px-EventSeriesIcon.png",
                "title": "EventSeries@scholia",
                "link": f"https://scholia.toolforge.org/event-series/{self.wd_event_series}",
                "valid": self.wd_event_series,
            },
            {
                "src": "/static/icons/32px-Wikidata_Query_Service_Favicon_wbg.svg.png",
                "title": "Proceedings@wikidata",
                "link": f"https://www.wikidata.org/wiki/{self.wikidataid}",
                "valid": self.wikidataid,
            },
            {
                "src": "/static/icons/32px-EventIcon.png",
                "title": "Event@wikidata",
                "link": f"https://www.wikidata.org/wiki/{self.wd_event}",
                "valid": self.wd_event,
            },
            {
                "src": "/static/icons/32px-EventSeriesIcon.png",
                "title": "EventSeries@wikidata",
                "link": f"https://www.wikidata.org/wiki/{self.wd_event_series}",
                "valid": self.wd_event_series,
            },
            {
                "src": "/static/icons/32px-SMW-icon.png",
                "title": "SMW markup",
                "link": f"/Vol-{self.number}.smw",
                "valid": True,
            },
            {
                "src": "/static/icons/32px-JSON_vector_logo.svg.png",
                "title": "JSON metadata",
                "link": f"/Vol-{self.number}.json",
                "valid": True,
            },
            {
                "src": "/static/icons/32px-YAML_Logo.svg.png",
                "title": "YML metadata",
                "link": f"/Vol-{self.number}.yaml",
                "valid": True,
            },
        ]
        icon_tag = Volume.create_icon_bar(soup, icon_list=icon_list)
        return icon_tag

    def addPaper(self, paper: "Paper"):
        """
        add the given paper
        """
        # @TODO fixme to use LinkML generated code
        self.papers.append(paper)
        paper.paper_index = len(self.papers) - 1

    def fix_element_tag(self, element, tag: str = "href", ext: str = ".pdf"):
        """
        fix the given element tag

        Args:
            tag(str): the tag to fix
            ext(str): the extension
        """
        org_tag_value = element[tag]
        value = org_tag_value.replace("http://ceur-ws.org/", "/")
        for file in ["ceur-ws.css", "CEUR-WS-logo.png"]:
            value = value.replace(f"../{file}", f"/static/{file}")
        if ".pdf" in value:
            value = value.replace(".pdf", ext)
            value = f"/Vol-{self.number}/{value}"
            pass
        element[tag] = value

    def add_volume_navigation(self, soup: BeautifulSoup):
        """
        Add navigation bar to volume number to jump to the volume below and above
        Args:
            soup: index page
        """
        vol_tag = soup.find("span", class_="CEURVOLNR")
        if vol_tag:
            prev_link = Volume.volLink_soup_tag(soup, self.number, -1)
            if prev_link:
                vol_tag.insert_before(prev_link)
            next_link = Volume.volLink_soup_tag(soup, self.number, +1)
            if next_link:
                vol_tag.insert_after(next_link)

    def get_empty_volume_page(self, content_html: str = None):
        """
        Get empty volume page
        """
        html_page = f"""
            <!DOCTYPE html>
            <!-- CEURVERSION=2020-07-09 -->
            <html lang="en">
            <head>
            <meta http-equiv="Content-type" content="text/html;charset=utf-8">
            <meta name="viewport" content="width=device-width, initial-scale=1.0">
            <link rel="stylesheet" type="text/css" href="/static/ceur-ws.css">
            </head>
            <!--CEURLANG=eng -->
            <body>

            <table style="border: 0; border-spacing: 0; border-collapse: collapse; width: 95%">
            <tbody><tr>
            <td style="text-align: left; vertical-align: middle">
            <a href="http://ceur-ws.org/"><div id="CEURWSLOGO"></div></a>
            </td>
            <td style="text-align: right; vertical-align: middle">
            <div style="float:left" id="CEURCCBY"></div>
            <span class="CEURVOLNR">Vol-{self.number}</span> <br>
            <span class="CEURURN">urn:nbn:de:0074-3365-4</span>
            </td>
            </tr>
            </tbody></table>
            {content_html}
            </body></html>
        """
        soup = BeautifulSoup(html_page, "html.parser")
        self.add_volume_navigation(soup)
        content = soup.prettify(formatter="html")
        return content

    def getHtml(self, ext: str = ".pdf", fixLinks: bool = True) -> str:
        """
        get my HTML content

        Args:
            ext(str): the extension to use for pdf page details
            fixLinks(bool): if True fix the links
        """
        index_path = f"{self.vol_dir}/index.html"
        try:
            with open(index_path, "r") as index_html:
                content = index_html.read()
                if fixLinks:
                    soup = BeautifulSoup(content, "html.parser")
                    for element in soup.findAll(["link", "a"]):
                        self.fix_element_tag(element, tag="href", ext=ext)
                    for element in soup.findAll(["image"]):
                        self.fix_element_tag(element, tag="src", ext=ext)
                    self.add_volume_navigation(soup)
                    first_hr = soup.find("hr")
                    if first_hr:
                        icon_bar = self.getIconBar(soup)
                        first_hr.insert_before(icon_bar)
                    content = soup.prettify(formatter="html")
            return content
        except Exception as ex:
            err_html = f"""<span style="color:red">reading {index_path} for Volume {self.number} failed: {str(ex)}</span>"""
            content = self.get_empty_volume_page(err_html)
            return content

    def as_smw_markup(self) -> str:
        """
        return my semantic mediawiki markup

        Returns:
            str: the smw markup for this volume
        """
        markup = f"""=Volume=
{{{{Volume
|number={self.number}
|storemode=property
|wikidataid={self.wikidataid}
|title={self.title}
|acronym={self.acronym}
|url={self.url}
|date={self.date}
"""
        for attr in ["dblp", "k10plus"]:
            value = getattr(self, attr)
            if value:
                markup += f"|{attr}={value}\n"
        markup += f"""|urn=urn:nbn:de:0074-1155-8
}}}}"""
        return markup

addPaper(paper)

add the given paper

Source code in ceurspt/ceurws.py 
805
806
807
808
809
810
811
def addPaper(self, paper: "Paper"):
    """
    add the given paper
    """
    # @TODO fixme to use LinkML generated code
    self.papers.append(paper)
    paper.paper_index = len(self.papers) - 1

add_volume_navigation(soup)

Add navigation bar to volume number to jump to the volume below and above Args: soup: index page

Source code in ceurspt/ceurws.py 
831
832
833
834
835
836
837
838
839
840
841
842
843
844
def add_volume_navigation(self, soup: BeautifulSoup):
    """
    Add navigation bar to volume number to jump to the volume below and above
    Args:
        soup: index page
    """
    vol_tag = soup.find("span", class_="CEURVOLNR")
    if vol_tag:
        prev_link = Volume.volLink_soup_tag(soup, self.number, -1)
        if prev_link:
            vol_tag.insert_before(prev_link)
        next_link = Volume.volLink_soup_tag(soup, self.number, +1)
        if next_link:
            vol_tag.insert_after(next_link)

as_smw_markup()

return my semantic mediawiki markup

Returns:

Name Type Description
str str

the smw markup for this volume
Source code in ceurspt/ceurws.py 
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
    def as_smw_markup(self) -> str:
        """
        return my semantic mediawiki markup

        Returns:
            str: the smw markup for this volume
        """
        markup = f"""=Volume=
{{{{Volume
|number={self.number}
|storemode=property
|wikidataid={self.wikidataid}
|title={self.title}
|acronym={self.acronym}
|url={self.url}
|date={self.date}
"""
        for attr in ["dblp", "k10plus"]:
            value = getattr(self, attr)
            if value:
                markup += f"|{attr}={value}\n"
        markup += f"""|urn=urn:nbn:de:0074-1155-8
}}}}"""
        return markup

create_icon_bar(soup, icon_list, class_name='icon_list') classmethod

Creates a new

tag with the specified class name and list of icons.

Parameters:

Name Type Description Default
soup BeautifulSoup

The BeautifulSoup object to use for creating new tags.

 required
icon_list List[Dict[str, str]]

The list of icons to add to the

tag. Each icon is represented as a dictionary with the following keys: - src (str): The URL of the icon image file. - title (str): The title text to use as a tooltip for the icon. - link (str): The URL to link to when the icon is clicked.

 required
class_name str

The name of the CSS class to apply to the

tag.

 'icon_list'

Returns:

Name Type Description
Tag Tag

The new

tag with the specified class name and list of icons.
Source code in ceurspt/ceurws.py 
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
@classmethod
def create_icon_bar(
    cls,
    soup: BeautifulSoup,
    icon_list: typing.List[typing.Dict[str, str]],
    class_name: str = "icon_list",
) -> "Tag":
    """
    Creates a new <div> tag with the specified class name and list of icons.

    Args:
        soup: The BeautifulSoup object to use for creating new tags.
        icon_list: The list of icons to add to the <div> tag. Each icon is represented as a
            dictionary with the following keys:
                - src (str): The URL of the icon image file.
                - title (str): The title text to use as a tooltip for the icon.
                - link (str): The URL to link to when the icon is clicked.
        class_name: The name of the CSS class to apply to the <div> tag.

    Returns:
        Tag: The new <div> tag with the specified class name and list of icons.
    """

    # create a new div tag
    div_tag = soup.new_tag("div")

    div_tag.append(soup.new_tag("hr"))

    # add the specified class name to the div tag
    div_tag["class"] = [class_name]

    for link_tag in cls.create_icon_list(soup, icon_list):
        # append the link tag to the div tag
        div_tag.append(link_tag)

    # return the div tag
    return div_tag

create_icon_list(soup, icon_list) classmethod

create a list of icons

Parameters:

Name Type Description Default
soup BeautifulSoup

The BeautifulSoup object to use for creating new tags.

 required
icon_list List[Dict[str, str]]

The list of icons to add to the

tag. Each icon is represented as a dictionary with the following keys: - src (str): The URL of the icon image file. - title (str): The title text to use as a tooltip for the icon. - link (str): The URL to link to when the icon is clicked.

 required

Returns:

Type Description
List[Tag]

a list of link_tags
Source code in ceurspt/ceurws.py 
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
@classmethod
def create_icon_list(
    cls, soup: BeautifulSoup, icon_list: typing.List[typing.Dict[str, str]]
) -> typing.List["Tag"]:
    """
    create a list of icons

    Args:
        soup: The BeautifulSoup object to use for creating new tags.
        icon_list: The list of icons to add to the <div> tag. Each icon is represented as a
            dictionary with the following keys:
                - src (str): The URL of the icon image file.
                - title (str): The title text to use as a tooltip for the icon.
                - link (str): The URL to link to when the icon is clicked.

    Returns:
        a list of link_tags
    """
    link_tags = []
    # iterate over the icon list and create a new tag for each icon
    for icon_data in icon_list:
        # create a new a tag for the link
        link_tag = soup.new_tag("a")
        link_tag["href"] = icon_data["link"]
        # open link in new tab
        link_tag["target"] = "_blank"
        if not icon_data["valid"]:
            link_tag["style"] = "filter: grayscale(1);"

        # create a new img tag for the icon
        icon_tag = soup.new_tag("img")

        # add the icon attributes to the img tag
        icon_tag["src"] = icon_data["src"]
        icon_tag["title"] = icon_data["title"]

        # append the icon tag to the link tag
        link_tag.append(icon_tag)
        link_tags.append(link_tag)
    return link_tags

fix_element_tag(element, tag='href', ext='.pdf')

fix the given element tag

Parameters:

Name Type Description Default
tag(str)

the tag to fix

 required
ext(str)

the extension

 required
Source code in ceurspt/ceurws.py 
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
def fix_element_tag(self, element, tag: str = "href", ext: str = ".pdf"):
    """
    fix the given element tag

    Args:
        tag(str): the tag to fix
        ext(str): the extension
    """
    org_tag_value = element[tag]
    value = org_tag_value.replace("http://ceur-ws.org/", "/")
    for file in ["ceur-ws.css", "CEUR-WS-logo.png"]:
        value = value.replace(f"../{file}", f"/static/{file}")
    if ".pdf" in value:
        value = value.replace(".pdf", ext)
        value = f"/Vol-{self.number}/{value}"
        pass
    element[tag] = value

getHtml(ext='.pdf', fixLinks=True)

get my HTML content

Parameters:

Name Type Description Default
ext(str)

the extension to use for pdf page details

 required
fixLinks(bool)

if True fix the links

 required
Source code in ceurspt/ceurws.py 
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
def getHtml(self, ext: str = ".pdf", fixLinks: bool = True) -> str:
    """
    get my HTML content

    Args:
        ext(str): the extension to use for pdf page details
        fixLinks(bool): if True fix the links
    """
    index_path = f"{self.vol_dir}/index.html"
    try:
        with open(index_path, "r") as index_html:
            content = index_html.read()
            if fixLinks:
                soup = BeautifulSoup(content, "html.parser")
                for element in soup.findAll(["link", "a"]):
                    self.fix_element_tag(element, tag="href", ext=ext)
                for element in soup.findAll(["image"]):
                    self.fix_element_tag(element, tag="src", ext=ext)
                self.add_volume_navigation(soup)
                first_hr = soup.find("hr")
                if first_hr:
                    icon_bar = self.getIconBar(soup)
                    first_hr.insert_before(icon_bar)
                content = soup.prettify(formatter="html")
        return content
    except Exception as ex:
        err_html = f"""<span style="color:red">reading {index_path} for Volume {self.number} failed: {str(ex)}</span>"""
        content = self.get_empty_volume_page(err_html)
        return content

getIconBar(soup)

get my icon bar

Parameters:

Name Type Description Default
soup

The BeautifulSoup object to use for creating new tags.

 required
Source code in ceurspt/ceurws.py 
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
def getIconBar(self, soup):
    """
    get my icon bar

    Parameters:
        soup: The BeautifulSoup object to use for creating new tags.
    """
    volume_record = self.vm.getVolumeRecord(self.number)
    for wd_key, attr in [
        ("wd.event", "wd_event"),
        ("wd.eventSeries", "wd_event_series"),
    ]:
        value = None
        if wd_key in volume_record:
            value = volume_record[wd_key]
            if value:
                value = value.replace("http://www.wikidata.org/entity/", "")
        setattr(self, attr, value)
    # create a list of icons to add to the div
    icon_list = [
        {
            "src": "/static/icons/32px-dblp-icon.png",
            "title": "dblp",
            "link": f"https://dblp.org/rec/{self.dblp}",
            "valid": self.dblp,
        },
        {
            "src": "/static/icons/32px-DNB.svg.png",
            "title": "k10plus/DNB",
            "link": f"https://opac.k10plus.de/DB=2.299/PPNSET?PPN={self.k10plus}",
            "valid": self.k10plus,
        },
        {
            "src": "/static/icons/32px-Scholia_logo.svg.png",
            "title": "Proceedings@scholia",
            "link": f"https://scholia.toolforge.org/venue/{self.wikidataid}",
            "valid": self.wikidataid,
        },
        {
            "src": "/static/icons/32px-EventIcon.png",
            "title": "Event@scholia",
            "link": f"https://scholia.toolforge.org/event/{self.wd_event}",
            "valid": self.wd_event,
        },
        {
            "src": "/static/icons/32px-EventSeriesIcon.png",
            "title": "EventSeries@scholia",
            "link": f"https://scholia.toolforge.org/event-series/{self.wd_event_series}",
            "valid": self.wd_event_series,
        },
        {
            "src": "/static/icons/32px-Wikidata_Query_Service_Favicon_wbg.svg.png",
            "title": "Proceedings@wikidata",
            "link": f"https://www.wikidata.org/wiki/{self.wikidataid}",
            "valid": self.wikidataid,
        },
        {
            "src": "/static/icons/32px-EventIcon.png",
            "title": "Event@wikidata",
            "link": f"https://www.wikidata.org/wiki/{self.wd_event}",
            "valid": self.wd_event,
        },
        {
            "src": "/static/icons/32px-EventSeriesIcon.png",
            "title": "EventSeries@wikidata",
            "link": f"https://www.wikidata.org/wiki/{self.wd_event_series}",
            "valid": self.wd_event_series,
        },
        {
            "src": "/static/icons/32px-SMW-icon.png",
            "title": "SMW markup",
            "link": f"/Vol-{self.number}.smw",
            "valid": True,
        },
        {
            "src": "/static/icons/32px-JSON_vector_logo.svg.png",
            "title": "JSON metadata",
            "link": f"/Vol-{self.number}.json",
            "valid": True,
        },
        {
            "src": "/static/icons/32px-YAML_Logo.svg.png",
            "title": "YML metadata",
            "link": f"/Vol-{self.number}.yaml",
            "valid": True,
        },
    ]
    icon_tag = Volume.create_icon_bar(soup, icon_list=icon_list)
    return icon_tag

getMergedDict()

get my merged dict

Returns:

Type Description
dict

dict
Source code in ceurspt/ceurws.py 
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
def getMergedDict(self) -> dict:
    """
    get my merged dict

    Returns:
        dict
    """
    my_dict = dataclasses.asdict(self)
    m_dict = {
        "version.version": Version.version,
        "version.cm_url": Version.cm_url,
        "spt.html_url": f"/Vol-{self.number}.html",
    }
    for key, value in my_dict.items():
        m_dict[f"spt.{key}"] = value
    volrecord = self.vm.getVolumeRecord(self.number)
    for key, value in volrecord.items():
        if "." in key:
            m_dict[f"{key}"] = value
        else:
            m_dict[f"cvb.{key}"] = value
    return m_dict

get_empty_volume_page(content_html=None)

Get empty volume page

Source code in ceurspt/ceurws.py 
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
def get_empty_volume_page(self, content_html: str = None):
    """
    Get empty volume page
    """
    html_page = f"""
        <!DOCTYPE html>
        <!-- CEURVERSION=2020-07-09 -->
        <html lang="en">
        <head>
        <meta http-equiv="Content-type" content="text/html;charset=utf-8">
        <meta name="viewport" content="width=device-width, initial-scale=1.0">
        <link rel="stylesheet" type="text/css" href="/static/ceur-ws.css">
        </head>
        <!--CEURLANG=eng -->
        <body>

        <table style="border: 0; border-spacing: 0; border-collapse: collapse; width: 95%">
        <tbody><tr>
        <td style="text-align: left; vertical-align: middle">
        <a href="http://ceur-ws.org/"><div id="CEURWSLOGO"></div></a>
        </td>
        <td style="text-align: right; vertical-align: middle">
        <div style="float:left" id="CEURCCBY"></div>
        <span class="CEURVOLNR">Vol-{self.number}</span> <br>
        <span class="CEURURN">urn:nbn:de:0074-3365-4</span>
        </td>
        </tr>
        </tbody></table>
        {content_html}
        </body></html>
    """
    soup = BeautifulSoup(html_page, "html.parser")
    self.add_volume_navigation(soup)
    content = soup.prettify(formatter="html")
    return content

get a relative volume link

Parameters:

Name Type Description Default
number(int)

the volume number

 required
inc(int)

the relative increment

 required

Returns(str): a relative volume link

Source code in ceurspt/ceurws.py 
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
@classmethod
def volLink(cls, number: int, inc: int = 0) -> str:
    """
    get a relative volume link

    Args:
        number(int): the volume number
        inc(int): the relative increment

    Returns(str):
        a relative volume link
    """
    href, text = cls.volLinkParts(number, inc)
    if number > 0:
        link = f"""<a href="{href}">{text}</a>"""
    else:
        link = ""
    return link

volLinkParts(number, inc=0) classmethod

a relative volume link

Source code in ceurspt/ceurws.py 
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
@classmethod
def volLinkParts(cls, number: int, inc: int = 0):
    """
    a relative volume link
    """
    if inc > 0:
        presymbol = "⫸"
        postsymbol = ""
    elif inc < 0:
        presymbol = ""
        postsymbol = "â«·"
    else:
        presymbol = ""
        postsymbol = ""
    href = f"/Vol-{number+inc}.html"
    text = f"{presymbol}Vol-{number+inc}{postsymbol}"
    return href, text

get a relative volume link as a soup tag

Parameters:

Name Type Description Default
soup(BeautifulSoup)

the soup

 required
number(int)

the volume number

 required
inc(int)

the relative increment

 required

Returns(str): a relative volume link

Source code in ceurspt/ceurws.py 
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
@classmethod
def volLink_soup_tag(cls, soup, number: int, inc: int = 0) -> str:
    """
    get a relative volume link as a soup tag

    Args:
        soup(BeautifulSoup): the soup
        number(int): the volume number
        inc(int): the relative increment

    Returns(str):
        a relative volume link
    """
    href, text = cls.volLinkParts(number, inc)
    link = soup.new_tag("a", href=href)
    link.string = text
    return link

VolumeManager

Bases: JsonCacheManager

manage all volumes

Source code in ceurspt/ceurws.py 
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
class VolumeManager(JsonCacheManager):
    """
    manage all volumes
    """

    def __init__(self, base_path: str, base_url: str):
        """
        initialize me with the given base_path

        Args:
            base_path(str): the path to my files
            base_url(str): the url of the RESTFul metadata service
        """
        JsonCacheManager.__init__(self, base_url=base_url)
        self.base_path = base_path
        self.volumes_by_number: Dict[int, Volume] = {}
        self.volume_records_by_number: Dict[int, dict] = {}

    def head_table_html(self) -> str:
        """ """
        html = """<table width="97%" cellspacing="5" cellpadding="0" border="0">
<tbody><tr>
<td valign="middle" align="left">
<div id="CEURWSLOGO"></div>
<!--<img alt="[25years CEUR-WS]" style="padding:4px; float:left;"  width="550" src="./CEUR-WS-logo-originals/2020/CEUR-WS-25anniversary.png"> -->
</td>
<td valign="middle" align="justify">
<font size="-2" face="ARIAL,HELVETICA,VERDANA" color="#363636">

<img alt="[OpenAccess]" style="padding:6px; float:left;" src="/static/OpenAccesslogo_200x313.png" width="18">
CEUR Workshop Proceedings (CEUR-WS.org) is a
<a href="https://ceur-ws.org/CEURWS-VALUES.html">free</a>
<a href="http://www.sherpa.ac.uk/romeo/issn/1613-0073/">open-access</a>
publication service
at <a href="http://sunsite.informatik.rwth-aachen.de">Sun SITE Central Europe</a>
operated under the umbrella of
 <a href="http://www-i5.informatik.rwth-aachen.de">RWTH Aachen University</a>.
CEUR-WS.org is a recognized ISSN publication series,
<a href="https://ceur-ws.org/issn-1613-0073.html">ISSN 1613-0073</a> (<a href="https://portal.issn.org/resource/ISSN/1613-0073?format=json">json</a>).
CEUR-WS.org is hosted at http://SunSITE.Informatik.RWTH-Aachen.DE/Publications/CEUR-WS/.
This service is provided by
the <b><a href="https://ceur-ws.org/CEURWS-TEAM.html">CEUR-WS.org Team</a></b>.
See end of the page for contact details and <a href="https://ceur-ws.org/#IMPRESSUM">Impressum</a>.
</font>
</td>
</tr>
</tbody></table>"""
        return html

    def index_html(
        self, upper: Optional[int] = None, lower: Optional[int] = None
    ) -> str:
        """
        return an index going from the given upper volume number down to the given lower volume number

        Args:
            upper(int): upper volume number to start with
            lower(int): lower volume number to end with

        Returns:
            html code for index
        """
        html = f"""<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
   "https://www.w3.org/TR/html4/loose.dtd">
<html>
  <head> 
    <meta http-equiv="Content-Type" content="Type=text/html;charset=utf-8">
    <meta name="description" content="CEUR-WS.org provides free online scientific papers">
    <meta name="keywords" content="open access, open archive, free scientific paper, workshop proceedings, online publishing, computer science, information systems" >

    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <!-- automatically refresh daily-->
    <meta http-equiv="expires" content="86400">
    <link rel="stylesheet" type="text/css" href="/static/ceur-ws.css">
    <link rel="icon" type="image/x-icon" href="/static/favicon.ico">
    <title>CEUR-WS.org - CEUR Workshop Proceedings (free, open-access publishing, computer science/information systems)</title>
    <link rel="shortcut icon" href="/static/ceur-ws.ico">
  </head>
  <body>
     {self.head_table_html()}
     <div>
"""
        # prepare the indexing
        # get the volumes as a list from 1 - top e.g. 3365
        volumes = list(self.volumes_by_number.values())
        # reverse the list
        volumes.reverse()
        # make sure upper and lower values are valid
        if upper is None:
            upper = volumes[0].number
        if lower is None:
            lower = 1
        # loop over the reversed list
        for vol_index in range(len(volumes)):
            vol = volumes[vol_index]
            vol_number = vol.number
            if vol_number > upper:
                continue
            if vol_number < lower:
                break
            if isinstance(vol.title, str):
                vol_title = escape(vol.title)
            else:
                vol_title = "Title missing (Might be one of the empty volumes)"
            if vol_title is None:
                pass
            html += f"""       <div style='bgcolor:#DCDBD7'>
         <b><a name='Vol-{vol_number}'>Vol-{vol_number}</a></b>
         <a href='/Vol-{vol_number}.html'>{vol_title}</a>
       </div>
"""
        html += """    </div>
  </body>
</html>"""
        return html

    def getVolume(self, number: int):
        """
        get my volume by volume number

        Args:
            number(int): the volume to get
        """
        if number in self.volumes_by_number:
            return self.volumes_by_number[number]
        else:
            return None

    def getVolumeRecord(self, number: int):
        if number in self.volume_records_by_number:
            return self.volume_records_by_number[number]
        else:
            return None

    def getVolumes(self, verbose: bool = False):
        """
        get my volumes

        Args:
            verbose(bool): if True show verbose loading information
        """
        profiler = Profiler("Loading volumes", profile=verbose)
        volume_lod = self.load_lod("volumes")
        proceedings_lod = self.load_lod("proceedings")
        self.volumes_by_number = {}
        self.volume_records_by_number = {}
        for volume_record in volume_lod:
            vol_number = volume_record["number"]
            self.volume_records_by_number[vol_number] = volume_record
            title = volume_record["title"]
            pub_date_str = volume_record["pubDate"]
            if pub_date_str:
                pub_date = datetime.fromisoformat(pub_date_str).date()
            else:
                pub_date = None
            acronym = volume_record["acronym"]
            volume = Volume(
                number=vol_number, title=title, date=pub_date, acronym=acronym
            )
            volume.vm = self
            volume.number = int(volume.number)
            vol_dir = f"{self.base_path}/Vol-{vol_number}"
            if os.path.isdir(vol_dir):
                volume.vol_dir = vol_dir
            else:
                volume.vol_dir = None
            self.volumes_by_number[vol_number] = volume
        for proc_record in proceedings_lod:
            number = proc_record["sVolume"]
            if not number:
                print(f"Warning: {proc_record} has no volume number")
            else:
                volume_record = self.volume_records_by_number[number]
                volume = self.volumes_by_number[number]
                for key, value in proc_record.items():
                    volume_record[f"wd.{key}"] = value
                map_pairs = [
                    ("item", "wikidataid"),
                    ("itemDescription", "description"),
                    ("dblpProceedingsId", "dblp"),
                    ("described_at_URL", "url"),
                    ("ppnId", "k10plus"),
                    ("URN_NBN", "urn"),
                ]
                for wd_id, attr in map_pairs:
                    wd_key = f"wd.{wd_id}"
                    if wd_key in volume_record:
                        value = volume_record[wd_key]
                        if isinstance(value, str):
                            value = value.replace("http://www.wikidata.org/entity/", "")
                            value = value.replace("https://www.wikidata.org/wiki/", "")
                        setattr(volume, attr, value)
                        pass
        msg = f"{len(self.volumes_by_number)} volumes"
        profiler.time(msg)

__init__(base_path, base_url)

initialize me with the given base_path

Parameters:

Name Type Description Default
base_path(str)

the path to my files

 required
base_url(str)

the url of the RESTFul metadata service

 required
Source code in ceurspt/ceurws.py 
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
def __init__(self, base_path: str, base_url: str):
    """
    initialize me with the given base_path

    Args:
        base_path(str): the path to my files
        base_url(str): the url of the RESTFul metadata service
    """
    JsonCacheManager.__init__(self, base_url=base_url)
    self.base_path = base_path
    self.volumes_by_number: Dict[int, Volume] = {}
    self.volume_records_by_number: Dict[int, dict] = {}

getVolume(number)

get my volume by volume number

Parameters:

Name Type Description Default
number(int)

the volume to get

 required
Source code in ceurspt/ceurws.py 
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
def getVolume(self, number: int):
    """
    get my volume by volume number

    Args:
        number(int): the volume to get
    """
    if number in self.volumes_by_number:
        return self.volumes_by_number[number]
    else:
        return None

getVolumes(verbose=False)

get my volumes

Parameters:

Name Type Description Default
verbose(bool)

if True show verbose loading information

 required
Source code in ceurspt/ceurws.py 
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
def getVolumes(self, verbose: bool = False):
    """
    get my volumes

    Args:
        verbose(bool): if True show verbose loading information
    """
    profiler = Profiler("Loading volumes", profile=verbose)
    volume_lod = self.load_lod("volumes")
    proceedings_lod = self.load_lod("proceedings")
    self.volumes_by_number = {}
    self.volume_records_by_number = {}
    for volume_record in volume_lod:
        vol_number = volume_record["number"]
        self.volume_records_by_number[vol_number] = volume_record
        title = volume_record["title"]
        pub_date_str = volume_record["pubDate"]
        if pub_date_str:
            pub_date = datetime.fromisoformat(pub_date_str).date()
        else:
            pub_date = None
        acronym = volume_record["acronym"]
        volume = Volume(
            number=vol_number, title=title, date=pub_date, acronym=acronym
        )
        volume.vm = self
        volume.number = int(volume.number)
        vol_dir = f"{self.base_path}/Vol-{vol_number}"
        if os.path.isdir(vol_dir):
            volume.vol_dir = vol_dir
        else:
            volume.vol_dir = None
        self.volumes_by_number[vol_number] = volume
    for proc_record in proceedings_lod:
        number = proc_record["sVolume"]
        if not number:
            print(f"Warning: {proc_record} has no volume number")
        else:
            volume_record = self.volume_records_by_number[number]
            volume = self.volumes_by_number[number]
            for key, value in proc_record.items():
                volume_record[f"wd.{key}"] = value
            map_pairs = [
                ("item", "wikidataid"),
                ("itemDescription", "description"),
                ("dblpProceedingsId", "dblp"),
                ("described_at_URL", "url"),
                ("ppnId", "k10plus"),
                ("URN_NBN", "urn"),
            ]
            for wd_id, attr in map_pairs:
                wd_key = f"wd.{wd_id}"
                if wd_key in volume_record:
                    value = volume_record[wd_key]
                    if isinstance(value, str):
                        value = value.replace("http://www.wikidata.org/entity/", "")
                        value = value.replace("https://www.wikidata.org/wiki/", "")
                    setattr(volume, attr, value)
                    pass
    msg = f"{len(self.volumes_by_number)} volumes"
    profiler.time(msg)

head_table_html()

Source code in ceurspt/ceurws.py 
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
    def head_table_html(self) -> str:
        """ """
        html = """<table width="97%" cellspacing="5" cellpadding="0" border="0">
<tbody><tr>
<td valign="middle" align="left">
<div id="CEURWSLOGO"></div>
<!--<img alt="[25years CEUR-WS]" style="padding:4px; float:left;"  width="550" src="./CEUR-WS-logo-originals/2020/CEUR-WS-25anniversary.png"> -->
</td>
<td valign="middle" align="justify">
<font size="-2" face="ARIAL,HELVETICA,VERDANA" color="#363636">

<img alt="[OpenAccess]" style="padding:6px; float:left;" src="/static/OpenAccesslogo_200x313.png" width="18">
CEUR Workshop Proceedings (CEUR-WS.org) is a
<a href="https://ceur-ws.org/CEURWS-VALUES.html">free</a>
<a href="http://www.sherpa.ac.uk/romeo/issn/1613-0073/">open-access</a>
publication service
at <a href="http://sunsite.informatik.rwth-aachen.de">Sun SITE Central Europe</a>
operated under the umbrella of
 <a href="http://www-i5.informatik.rwth-aachen.de">RWTH Aachen University</a>.
CEUR-WS.org is a recognized ISSN publication series,
<a href="https://ceur-ws.org/issn-1613-0073.html">ISSN 1613-0073</a> (<a href="https://portal.issn.org/resource/ISSN/1613-0073?format=json">json</a>).
CEUR-WS.org is hosted at http://SunSITE.Informatik.RWTH-Aachen.DE/Publications/CEUR-WS/.
This service is provided by
the <b><a href="https://ceur-ws.org/CEURWS-TEAM.html">CEUR-WS.org Team</a></b>.
See end of the page for contact details and <a href="https://ceur-ws.org/#IMPRESSUM">Impressum</a>.
</font>
</td>
</tr>
</tbody></table>"""
        return html

index_html(upper=None, lower=None)

return an index going from the given upper volume number down to the given lower volume number

Parameters:

Name Type Description Default
upper(int)

upper volume number to start with

 required
lower(int)

lower volume number to end with

 required

Returns:

Type Description
str

html code for index
Source code in ceurspt/ceurws.py 
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
    def index_html(
        self, upper: Optional[int] = None, lower: Optional[int] = None
    ) -> str:
        """
        return an index going from the given upper volume number down to the given lower volume number

        Args:
            upper(int): upper volume number to start with
            lower(int): lower volume number to end with

        Returns:
            html code for index
        """
        html = f"""<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
   "https://www.w3.org/TR/html4/loose.dtd">
<html>
  <head> 
    <meta http-equiv="Content-Type" content="Type=text/html;charset=utf-8">
    <meta name="description" content="CEUR-WS.org provides free online scientific papers">
    <meta name="keywords" content="open access, open archive, free scientific paper, workshop proceedings, online publishing, computer science, information systems" >

    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <!-- automatically refresh daily-->
    <meta http-equiv="expires" content="86400">
    <link rel="stylesheet" type="text/css" href="/static/ceur-ws.css">
    <link rel="icon" type="image/x-icon" href="/static/favicon.ico">
    <title>CEUR-WS.org - CEUR Workshop Proceedings (free, open-access publishing, computer science/information systems)</title>
    <link rel="shortcut icon" href="/static/ceur-ws.ico">
  </head>
  <body>
     {self.head_table_html()}
     <div>
"""
        # prepare the indexing
        # get the volumes as a list from 1 - top e.g. 3365
        volumes = list(self.volumes_by_number.values())
        # reverse the list
        volumes.reverse()
        # make sure upper and lower values are valid
        if upper is None:
            upper = volumes[0].number
        if lower is None:
            lower = 1
        # loop over the reversed list
        for vol_index in range(len(volumes)):
            vol = volumes[vol_index]
            vol_number = vol.number
            if vol_number > upper:
                continue
            if vol_number < lower:
                break
            if isinstance(vol.title, str):
                vol_title = escape(vol.title)
            else:
                vol_title = "Title missing (Might be one of the empty volumes)"
            if vol_title is None:
                pass
            html += f"""       <div style='bgcolor:#DCDBD7'>
         <b><a name='Vol-{vol_number}'>Vol-{vol_number}</a></b>
         <a href='/Vol-{vol_number}.html'>{vol_title}</a>
       </div>
"""
        html += """    </div>
  </body>
</html>"""
        return html

ceurws_base

Boolean

Bases: Bool

A binary (true or false) value

Source code in ceurspt/ceurws_base.py 
84
85
86
87
88
89
90
class Boolean(Bool):
    """A binary (true or false) value"""

    type_class_uri = XSD.boolean
    type_class_curie = "xsd:boolean"
    type_name = "boolean"
    type_model_uri = CEURWSSCHEMA.Boolean

Date

Bases: XSDDate

a date (year, month and day) in an idealized calendar

Source code in ceurspt/ceurws_base.py 
129
130
131
132
133
134
135
class Date(XSDDate):
    """a date (year, month and day) in an idealized calendar"""

    type_class_uri = XSD.date
    type_class_curie = "xsd:date"
    type_name = "date"
    type_model_uri = CEURWSSCHEMA.Date

DateOrDatetime

Bases: str

Either a date or a datetime

Source code in ceurspt/ceurws_base.py 
147
148
149
150
151
152
153
class DateOrDatetime(str):
    """Either a date or a datetime"""

    type_class_uri = LINKML.DateOrDatetime
    type_class_curie = "linkml:DateOrDatetime"
    type_name = "date_or_datetime"
    type_model_uri = CEURWSSCHEMA.DateOrDatetime

Datetime

Bases: XSDDateTime

The combination of a date and time

Source code in ceurspt/ceurws_base.py 
138
139
140
141
142
143
144
class Datetime(XSDDateTime):
    """The combination of a date and time"""

    type_class_uri = XSD.dateTime
    type_class_curie = "xsd:dateTime"
    type_name = "datetime"
    type_model_uri = CEURWSSCHEMA.Datetime

Double

Bases: float

A real number that conforms to the xsd:double specification

Source code in ceurspt/ceurws_base.py 
102
103
104
105
106
107
108
class Double(float):
    """A real number that conforms to the xsd:double specification"""

    type_class_uri = XSD.double
    type_class_curie = "xsd:double"
    type_name = "double"
    type_model_uri = CEURWSSCHEMA.Double

Float

Bases: float

A real number that conforms to the xsd:float specification

Source code in ceurspt/ceurws_base.py 
93
94
95
96
97
98
99
class Float(float):
    """A real number that conforms to the xsd:float specification"""

    type_class_uri = XSD.float
    type_class_curie = "xsd:float"
    type_name = "float"
    type_model_uri = CEURWSSCHEMA.Float

Integer

Bases: int

An integer

Source code in ceurspt/ceurws_base.py 
75
76
77
78
79
80
81
class Integer(int):
    """An integer"""

    type_class_uri = XSD.integer
    type_class_curie = "xsd:integer"
    type_name = "integer"
    type_model_uri = CEURWSSCHEMA.Integer

Ncname

Bases: NCName

Prefix part of CURIE

Source code in ceurspt/ceurws_base.py 
174
175
176
177
178
179
180
class Ncname(NCName):
    """Prefix part of CURIE"""

    type_class_uri = XSD.string
    type_class_curie = "xsd:string"
    type_name = "ncname"
    type_model_uri = CEURWSSCHEMA.Ncname

Nodeidentifier

Bases: NodeIdentifier

A URI, CURIE or BNODE that represents a node in a model.

Source code in ceurspt/ceurws_base.py 
192
193
194
195
196
197
198
class Nodeidentifier(NodeIdentifier):
    """A URI, CURIE or BNODE that represents a node in a model."""

    type_class_uri = SHEX.nonLiteral
    type_class_curie = "shex:nonLiteral"
    type_name = "nodeidentifier"
    type_model_uri = CEURWSSCHEMA.Nodeidentifier

Objectidentifier

Bases: ElementIdentifier

A URI or CURIE that represents an object in the model.

Source code in ceurspt/ceurws_base.py 
183
184
185
186
187
188
189
class Objectidentifier(ElementIdentifier):
    """A URI or CURIE that represents an object in the model."""

    type_class_uri = SHEX.iri
    type_class_curie = "shex:iri"
    type_name = "objectidentifier"
    type_model_uri = CEURWSSCHEMA.Objectidentifier

Paper dataclass

Bases: YAMLRoot

A paper is e.g. a scholarly article

Source code in ceurspt/ceurws_base.py 
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
@dataclass
class Paper(YAMLRoot):
    """
    A paper is e.g. a scholarly article
    """

    _inherited_slots: ClassVar[List[str]] = []

    class_class_uri: ClassVar[URIRef] = CEURWSSCHEMA.Paper
    class_class_curie: ClassVar[str] = "CeurwsSchema:Paper"
    class_name: ClassVar[str] = "Paper"
    class_model_uri: ClassVar[URIRef] = CEURWSSCHEMA.Paper

    description: Optional[str] = None
    id: Optional[str] = None
    wikidataid: Optional[str] = None
    title: Optional[str] = None
    pdfUrl: Optional[Union[str, URI]] = None
    volume: Optional[Union[dict, Volume]] = None
    session: Optional[Union[dict, Session]] = None

    def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
        if self.description is not None and not isinstance(self.description, str):
            self.description = str(self.description)

        if self.id is not None and not isinstance(self.id, str):
            self.id = str(self.id)

        if self.wikidataid is not None and not isinstance(self.wikidataid, str):
            self.wikidataid = str(self.wikidataid)

        if self.title is not None and not isinstance(self.title, str):
            self.title = str(self.title)

        if self.pdfUrl is not None and not isinstance(self.pdfUrl, URI):
            self.pdfUrl = URI(self.pdfUrl)

        if self.volume is not None and not isinstance(self.volume, Volume):
            self.volume = Volume(**as_dict(self.volume))

        if self.session is not None and not isinstance(self.session, Session):
            self.session = Session(**as_dict(self.session))

        super().__post_init__(**kwargs)

Session dataclass

Bases: YAMLRoot

A Session is a a collection of papers as part of a Volume

Source code in ceurspt/ceurws_base.py 
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
@dataclass
class Session(YAMLRoot):
    """
    A Session is a a collection of papers as part of a Volume
    """

    _inherited_slots: ClassVar[List[str]] = []

    class_class_uri: ClassVar[URIRef] = CEURWSSCHEMA.Session
    class_class_curie: ClassVar[str] = "CeurwsSchema:Session"
    class_name: ClassVar[str] = "Session"
    class_model_uri: ClassVar[URIRef] = CEURWSSCHEMA.Session

    title: Optional[str] = None
    volume: Optional[Union[dict, Volume]] = None

    def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
        if self.title is not None and not isinstance(self.title, str):
            self.title = str(self.title)

        if self.volume is not None and not isinstance(self.volume, Volume):
            self.volume = Volume(**as_dict(self.volume))

        super().__post_init__(**kwargs)

String

Bases: str

A character string

Source code in ceurspt/ceurws_base.py 
66
67
68
69
70
71
72
class String(str):
    """A character string"""

    type_class_uri = XSD.string
    type_class_curie = "xsd:string"
    type_name = "string"
    type_model_uri = CEURWSSCHEMA.String

Time

Bases: XSDTime

A time object represents a (local) time of day, independent of any particular day

Source code in ceurspt/ceurws_base.py 
120
121
122
123
124
125
126
class Time(XSDTime):
    """A time object represents a (local) time of day, independent of any particular day"""

    type_class_uri = XSD.dateTime
    type_class_curie = "xsd:dateTime"
    type_name = "time"
    type_model_uri = CEURWSSCHEMA.Time

Uri

Bases: URI

a complete URI

Source code in ceurspt/ceurws_base.py 
165
166
167
168
169
170
171
class Uri(URI):
    """a complete URI"""

    type_class_uri = XSD.anyURI
    type_class_curie = "xsd:anyURI"
    type_name = "uri"
    type_model_uri = CEURWSSCHEMA.Uri

Uriorcurie

Bases: URIorCURIE

a URI or a CURIE

Source code in ceurspt/ceurws_base.py 
156
157
158
159
160
161
162
class Uriorcurie(URIorCURIE):
    """a URI or a CURIE"""

    type_class_uri = XSD.anyURI
    type_class_curie = "xsd:anyURI"
    type_name = "uriorcurie"
    type_model_uri = CEURWSSCHEMA.Uriorcurie

Volume dataclass

Bases: YAMLRoot

A Volume is a collection of papers mostly documenting the results of an academic event

Source code in ceurspt/ceurws_base.py 
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
@dataclass
class Volume(YAMLRoot):
    """
    A Volume is a collection of papers mostly documenting the results of an academic event
    """

    _inherited_slots: ClassVar[List[str]] = []

    class_class_uri: ClassVar[URIRef] = CEURWSSCHEMA.Volume
    class_class_curie: ClassVar[str] = "CeurwsSchema:Volume"
    class_name: ClassVar[str] = "Volume"
    class_model_uri: ClassVar[URIRef] = CEURWSSCHEMA.Volume

    number: Optional[float] = None
    acronym: Optional[str] = None
    wikidataid: Optional[str] = None
    title: Optional[str] = None
    description: Optional[str] = None
    url: Optional[str] = None
    date: Optional[Union[str, XSDDate]] = None
    dblp: Optional[str] = None
    k10plus: Optional[str] = None
    urn: Optional[str] = None

    def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
        if self.number is not None and not isinstance(self.number, float):
            self.number = float(self.number)

        if self.acronym is not None and not isinstance(self.acronym, str):
            self.acronym = str(self.acronym)

        if self.wikidataid is not None and not isinstance(self.wikidataid, str):
            self.wikidataid = str(self.wikidataid)

        if self.title is not None and not isinstance(self.title, str):
            self.title = str(self.title)

        if self.description is not None and not isinstance(self.description, str):
            self.description = str(self.description)

        if self.url is not None and not isinstance(self.url, str):
            self.url = str(self.url)

        if self.date is not None and not isinstance(self.date, XSDDate):
            self.date = XSDDate(self.date)

        if self.dblp is not None and not isinstance(self.dblp, str):
            self.dblp = str(self.dblp)

        if self.k10plus is not None and not isinstance(self.k10plus, str):
            self.k10plus = str(self.k10plus)

        if self.urn is not None and not isinstance(self.urn, str):
            self.urn = str(self.urn)

        super().__post_init__(**kwargs)

dataclass_util

Created on 30.03.2023

@author: wf

DataClassUtil

https://gist.github.com/gatopeich/1efd3e1e4269e1e98fae9983bb914f22

https://stackoverflow.com/a/54769644/1497139

Source code in ceurspt/dataclass_util.py 
10
11
12
13
14
15
16
17
18
19
20
21
22
23
class DataClassUtil:
    """
    https://gist.github.com/gatopeich/1efd3e1e4269e1e98fae9983bb914f22

    https://stackoverflow.com/a/54769644/1497139
    """

    @classmethod
    def dataclass_from_dict(cls, klass, d):
        try:
            fieldtypes = {f.name: f.type for f in dataclasses.fields(klass)}
            return klass(**{f: cls.dataclass_from_dict(fieldtypes[f], d[f]) for f in d})
        except:
            return d  # Not a dataclass field

profiler

Created on 27.03.2023

@author: wf

Profiler

simple profiler

Source code in ceurspt/profiler.py 
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
class Profiler:
    """
    simple profiler
    """

    def __init__(self, msg, profile=True):
        """
        construct me with the given msg and profile active flag

        Args:
            msg(str): the message to show if profiling is active
            profile(bool): True if messages should be shown
        """
        self.msg = msg
        self.profile = profile
        self.starttime = time.time()
        if profile:
            print(f"Starting {msg} ...", flush=True)

    def time(self, extraMsg=""):
        """
        time the action and print if profile is active
        """
        elapsed = time.time() - self.starttime
        if self.profile:
            print(f"{self.msg}{extraMsg} took {elapsed:5.1f} s", flush=True)
        return elapsed

__init__(msg, profile=True)

construct me with the given msg and profile active flag

Parameters:

Name Type Description Default
msg(str)

the message to show if profiling is active

 required
profile(bool)

True if messages should be shown

 required
Source code in ceurspt/profiler.py 
15
16
17
18
19
20
21
22
23
24
25
26
27
def __init__(self, msg, profile=True):
    """
    construct me with the given msg and profile active flag

    Args:
        msg(str): the message to show if profiling is active
        profile(bool): True if messages should be shown
    """
    self.msg = msg
    self.profile = profile
    self.starttime = time.time()
    if profile:
        print(f"Starting {msg} ...", flush=True)

time(extraMsg='')

time the action and print if profile is active

Source code in ceurspt/profiler.py 
29
30
31
32
33
34
35
36
def time(self, extraMsg=""):
    """
    time the action and print if profile is active
    """
    elapsed = time.time() - self.starttime
    if self.profile:
        print(f"{self.msg}{extraMsg} took {elapsed:5.1f} s", flush=True)
    return elapsed

spt_cmd

Created on 2023-03-17

@author: wf

CeurSptCmd

command line interface for CEUR Single Point of Truth

Source code in ceurspt/spt_cmd.py 
 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
class CeurSptCmd:
    """
    command line interface for CEUR Single Point of Truth
    """

    def get_arg_parser(self, description: str, version_msg) -> ArgumentParser:
        """
        Setup command line argument parser

        Args:
            description(str): the description
            version_msg(str): the version message

        Returns:
            ArgumentParser: the argument parser
        """
        script_path = Path(__file__)
        base_path = f"{script_path.parent.parent}/ceur-ws"
        base_url = "http://cvb.bitplan.com"
        parser = ArgumentParser(
            description=description, formatter_class=RawDescriptionHelpFormatter
        )
        parser.add_argument(
            "-a",
            "--about",
            help="show about info [default: %(default)s]",
            action="store_true",
        )
        parser.add_argument(
            "-b",
            "--basepath",
            help="the base path to the ceur-ws volumes [default: %(default)s]",
            default=base_path,
        )
        parser.add_argument(
            "-bu",
            "--baseurl",
            help="the base url to use for the RESTFul metadata service [default: %(default)s]",
            default=base_url,
        )
        parser.add_argument(
            "-d",
            "--debug",
            dest="debug",
            action="store_true",
            help="show debug info [default: %(default)s]",
        )
        parser.add_argument(
            "-rc",
            "--recreate",
            action="store_true",
            help="reload caches e.g. volume table",
        )

        parser.add_argument(
            "-v",
            "--verbose",
            action="store_true",
            help="show verbose infos e.g. on startup [default: %(default)s]",
        )
        parser.add_argument(
            "--host",
            default=self.get_default_host(),
            help="the host to serve / listen from [default: %(default)s]",
        )
        parser.add_argument(
            "--port",
            type=int,
            default=9990,
            help="the port to serve from [default: %(default)s]",
        )
        parser.add_argument(
            "-s",
            "--serve",
            action="store_true",
            help="start webserver [default: %(default)s]",
        )
        parser.add_argument("-V", "--version", action="version", version=version_msg)
        return parser

    def get_default_host(self) -> str:
        """
        get the default host as the fully qualifying hostname
        of the computer the server runs on

        Returns:
            str: the hostname
        """
        host = socket.getfqdn()
        # work around https://github.com/python/cpython/issues/79345
        if (
            host
            == "1.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.ip6.arpa"
        ):
            host = "localhost"  # host="127.0.0.1"
        return host

    def recreate(self, args: Namespace):
        """
        recreate the caches

        Args:
            args(Arguments): command line arguments
        """
        jcm = JsonCacheManager(base_url=args.baseurl)
        for lod_name in [
            "volumes",
            "papers",
            "proceedings",
            "authors_dblp",
            "papers_dblp",
        ]:
            profiler = Profiler(f"read {lod_name} ...", profile=True)
            lod = jcm.load_lod(lod_name)
            _elapsed = profiler.time(f" read {len(lod)} {lod_name}")
            jcm.store(lod_name, lod)
            profiler = Profiler(f"store {lod_name} ...", profile=True)
            _elapsed = profiler.time(f" store {len(lod)} {lod_name}")

    def start(self, args: Namespace):
        """
        Args:
            args(Arguments): command line arguments
        """
        vm = VolumeManager(base_path=args.basepath, base_url=args.baseurl)
        vm.getVolumes(args.verbose)
        pm = PaperManager(base_url=args.baseurl)
        pm.getPapers(vm, args.verbose)
        ws = WebServer(vm, pm)
        uvicorn.run(ws.app, host=args.host, port=args.port)

get_arg_parser(description, version_msg)

Setup command line argument parser

Parameters:

Name Type Description Default
description(str)

the description

 required
version_msg(str)

the version message

 required

Returns:

Name Type Description
ArgumentParser ArgumentParser

the argument parser
Source code in ceurspt/spt_cmd.py 
 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
def get_arg_parser(self, description: str, version_msg) -> ArgumentParser:
    """
    Setup command line argument parser

    Args:
        description(str): the description
        version_msg(str): the version message

    Returns:
        ArgumentParser: the argument parser
    """
    script_path = Path(__file__)
    base_path = f"{script_path.parent.parent}/ceur-ws"
    base_url = "http://cvb.bitplan.com"
    parser = ArgumentParser(
        description=description, formatter_class=RawDescriptionHelpFormatter
    )
    parser.add_argument(
        "-a",
        "--about",
        help="show about info [default: %(default)s]",
        action="store_true",
    )
    parser.add_argument(
        "-b",
        "--basepath",
        help="the base path to the ceur-ws volumes [default: %(default)s]",
        default=base_path,
    )
    parser.add_argument(
        "-bu",
        "--baseurl",
        help="the base url to use for the RESTFul metadata service [default: %(default)s]",
        default=base_url,
    )
    parser.add_argument(
        "-d",
        "--debug",
        dest="debug",
        action="store_true",
        help="show debug info [default: %(default)s]",
    )
    parser.add_argument(
        "-rc",
        "--recreate",
        action="store_true",
        help="reload caches e.g. volume table",
    )

    parser.add_argument(
        "-v",
        "--verbose",
        action="store_true",
        help="show verbose infos e.g. on startup [default: %(default)s]",
    )
    parser.add_argument(
        "--host",
        default=self.get_default_host(),
        help="the host to serve / listen from [default: %(default)s]",
    )
    parser.add_argument(
        "--port",
        type=int,
        default=9990,
        help="the port to serve from [default: %(default)s]",
    )
    parser.add_argument(
        "-s",
        "--serve",
        action="store_true",
        help="start webserver [default: %(default)s]",
    )
    parser.add_argument("-V", "--version", action="version", version=version_msg)
    return parser

get_default_host()

get the default host as the fully qualifying hostname of the computer the server runs on

Returns:

Name Type Description
str str

the hostname
Source code in ceurspt/spt_cmd.py 
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
def get_default_host(self) -> str:
    """
    get the default host as the fully qualifying hostname
    of the computer the server runs on

    Returns:
        str: the hostname
    """
    host = socket.getfqdn()
    # work around https://github.com/python/cpython/issues/79345
    if (
        host
        == "1.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.ip6.arpa"
    ):
        host = "localhost"  # host="127.0.0.1"
    return host

recreate(args)

recreate the caches

Parameters:

Name Type Description Default
args(Arguments)

command line arguments

 required
Source code in ceurspt/spt_cmd.py 
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
def recreate(self, args: Namespace):
    """
    recreate the caches

    Args:
        args(Arguments): command line arguments
    """
    jcm = JsonCacheManager(base_url=args.baseurl)
    for lod_name in [
        "volumes",
        "papers",
        "proceedings",
        "authors_dblp",
        "papers_dblp",
    ]:
        profiler = Profiler(f"read {lod_name} ...", profile=True)
        lod = jcm.load_lod(lod_name)
        _elapsed = profiler.time(f" read {len(lod)} {lod_name}")
        jcm.store(lod_name, lod)
        profiler = Profiler(f"store {lod_name} ...", profile=True)
        _elapsed = profiler.time(f" store {len(lod)} {lod_name}")

start(args)

Parameters:

Name Type Description Default
args(Arguments)

command line arguments

 required
Source code in ceurspt/spt_cmd.py 
141
142
143
144
145
146
147
148
149
150
151
def start(self, args: Namespace):
    """
    Args:
        args(Arguments): command line arguments
    """
    vm = VolumeManager(base_path=args.basepath, base_url=args.baseurl)
    vm.getVolumes(args.verbose)
    pm = PaperManager(base_url=args.baseurl)
    pm.getPapers(vm, args.verbose)
    ws = WebServer(vm, pm)
    uvicorn.run(ws.app, host=args.host, port=args.port)

main(argv=None)

main program.

Source code in ceurspt/spt_cmd.py 
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
def main(argv=None):  # IGNORE:C0111
    """main program."""

    if argv is None:
        argv = sys.argv[1:]

    program_name = "ceurspt"
    program_version = f"v{Version.version}"
    program_build_date = str(Version.date)
    program_version_message = f"{program_name} ({program_version},{program_build_date})"

    args = None
    try:
        spt_cmd = CeurSptCmd()
        parser = spt_cmd.get_arg_parser(
            description=Version.license, version_msg=program_version_message
        )
        args = parser.parse_args(argv)
        if len(argv) < 1:
            parser.print_usage()
            sys.exit(1)
        if args.about:
            print(program_version_message)
            print(f"see {Version.doc_url}")
            webbrowser.open(Version.doc_url)
        if args.recreate:
            spt_cmd.recreate(args)
        elif args.serve:
            spt_cmd.start(args)

    except KeyboardInterrupt:
        ###
        # handle keyboard interrupt
        # ###
        return 1
    except Exception as e:
        if DEBUG:
            raise e
        indent = len(program_name) * " "
        sys.stderr.write(program_name + ": " + repr(e) + "\n")
        sys.stderr.write(indent + "  for help use --help")
        if args is None:
            print("args could not be parsed")
        elif args.debug:
            print(traceback.format_exc())
        return 2

version

Created on 2022-09-11

@author: wf

Version

Bases: object

Version handling for VolumeBrowser

Source code in ceurspt/version.py 
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
class Version(object):
    """
    Version handling for VolumeBrowser
    """

    name = ""
    version = ceurspt.__version__
    date = "2023-03-17"
    updated = "2023-12-29"
    description = ("CEUR-WS Single Point of Truth RestFUL server",)

    authors = "Tim Holzheim, Wolfgang Fahl"

    doc_url = "https://github.com/ceurws/ceur-spt"
    chat_url = "https://github.com/ceurws/ceur-spt/discussions"
    cm_url = "https://github.com/ceurws/ceur-spt"

    license = f"""Copyright 2023 contributors. All rights reserved.

  Licensed under the Apache License 2.0
  https://www.apache.org/licenses/LICENSE-2.0

  Distributed on an "AS IS" basis without warranties
  or conditions of any kind, either express or implied."""
    longDescription = f"""{name} version {version}
{description}

  Created by {authors} on {date} last updated {updated}"""

webserver

Created on 2023-03-17

@author: wf

WebServer

the webserver

Source code in ceurspt/webserver.py 
 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
class WebServer:
    """
    the webserver
    """

    def __init__(
        self, vm: VolumeManager, pm: PaperManager, static_directory: str = "static"
    ):
        """
        constructor

        Args:
            vm(VolumeManager): the volume manager to use
            pm(PaperManager): the paper manager to use
            static_directory(str): the directory for static html files to use
        """
        self.app = FastAPI()
        # https://fastapi.tiangolo.com/tutorial/static-files/
        self.app.mount(
            "/static", StaticFiles(directory=static_directory), name="static"
        )
        self.vm = vm
        self.pm = pm

        @self.app.get("/index.html/{upper:int}/{lower:int}")
        async def index_html(upper: Optional[int], lower: Optional[int]):
            content = self.vm.index_html(upper=upper, lower=lower)
            return HTMLResponse(content)

        @self.app.get("/index.html")
        async def full_index_html():
            return await index_html(upper=None, lower=None)

        @self.app.get("/Vol-{number:int}/{pdf_name:str}.pdf")
        async def paperPdf(number: int, pdf_name: str):
            """
            get the PDF for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            pdf = paper.getPdf()
            return FileResponse(pdf)

        @self.app.get("/Vol-{number:int}/{pdf_name}.json")
        async def paperJson(number: int, pdf_name: str):
            """
            get the json response for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            paper_dict = paper.getMergedDict()
            return paper_dict

        @self.app.get("/Vol-{number:int}/{pdf_name}.wbjson")
        async def paperWikibaseCliJson(number: int, pdf_name: str):
            """
            get the json response to the wikibase-cli for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            paper_dict = paper.as_wb_dict()
            return paper_dict

        @self.app.get("/Vol-{number:int}/{pdf_name}/{qid}.wbcli")
        async def paperWikibaseCli(number: int, pdf_name, qid: str):
            """
            get the json response to the wikibase-cli for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            paper_cli_text = paper.as_wbi_cli_text(qid)
            return PlainTextResponse(paper_cli_text)

        @self.app.get("/Vol-{number:int}/{pdf_name}.html")
        async def paperHtml(number: int, pdf_name: str):
            """
            get the html response for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            content = paper.asHtml()
            return HTMLResponse(content=content)

        @self.app.get("/Vol-{number:int}/{pdf_name}.txt")
        async def paperText(number: int, pdf_name: str):
            """
            get the text for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            text = paper.getText()
            return PlainTextResponse(text)

        @self.app.get("/Vol-{number:int}/{pdf_name}.smw")
        async def paperSMW(number: int, pdf_name: str):
            """
            Get semantic media wiki markup of the given paper"""
            paper = self.getPaper(number, pdf_name)
            if paper:
                markup = paper.as_smw_markup()
            else:
                markup = f"""{{{{Paper
|id=Vol-{number}/{pdf_name}
|volume=Vol-{number}
}}}}"""
            return PlainTextResponse(markup)

        @self.app.get("/Vol-{number:int}/{pdf_name}.qs")
        async def paperQuickStatementns(number: int, pdf_name: str):
            """
            get the quickstatements for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            qs = paper.as_quickstatements()
            return PlainTextResponse(qs)

        @self.app.get("/Vol-{number:int}/{pdf_name}.grobid")
        async def paperGrobidXml(number: int, pdf_name: str):
            """
            get the grobid XML for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            xml = paper.getContentByPostfix(".tei.xml")
            return Response(content=xml, media_type="application/xml")

        @self.app.get("/Vol-{number:int}/{pdf_name}.cermine")
        async def paperCermineXml(number: int, pdf_name: str):
            """
            get the grobid XML for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            xml = paper.getContentByPostfix(".cermine.xml")
            return Response(content=xml, media_type="application/xml")

        @self.app.get("/Vol-{number:int}.smw")
        async def volumeSMW(number: int):
            """
            Get semantic media wiki markup of volume by given id
            """
            vol = self.getVolume(number)
            if vol:
                markup = vol.as_smw_markup()
            else:
                markup = f"{{{{Volume|number={number}}}}}"
            return PlainTextResponse(markup)

        @self.app.get("/Vol-{number:int}.json")
        async def volumeJson(number: int):
            """
            Get metadata of volume by given id
            """
            vol = self.getVolume(number)
            if vol:
                return vol.getMergedDict()
            else:
                return {"error": f"unknown volume number {number}"}

        @self.app.get("/Vol-{number:int}")
        async def volumeHtmlWithPdf(number: int):
            """
            get html Response for the given volume by number
            displaying pdfs directly
            """
            return self.volumeHtml(number, ext=".pdf")

        @self.app.get("/Vol-{number:int}.html")
        async def volumeHtmlWithHtml(number: int):
            """
            get html Response for the given volume by number
            displaying pdfs embedded in html
            """
            return self.volumeHtml(number, ext=".html")

        @self.app.get("/")
        async def home():
            """
            Return the home
            """
            url = "https://github.com/ceurws/ceur-spt"
            response = RedirectResponse(url=url, status_code=302)
            return response

        @self.app.get("/volume/{number:int}", tags=["json"])
        async def volume_citation(number: int):
            """
            Get volume record
            """
            vol = self.getVolume(number)
            if vol:
                record = vol.getMergedDict()
                return record
            else:
                return {"error": f"unknown volume number {number}"}

        @self.app.get("/volume/{number:int}/paper", tags=["json"])
        async def volume_citation_paper_by_number(number: int):
            """
            Get volume papers
            """
            vol = self.getVolume(number)
            if vol:
                paper_records = []
                for paper in vol.papers:
                    paper_records.append(paper.getMergedDict())
                return paper_records
            else:
                return {"error": f"unknown volume number {number}"}

        @self.app.get("/volume/{number:int}/citation", tags=["citation"])
        async def volume_citation_citation(number: int):
            """
            Get volume citation
            """
            vol = self.getVolume(number)
            if vol:
                citation = BibTexConverter.convert_volume(vol)
                return PlainTextResponse(content=citation)
            else:
                return {"error": f"unknown volume number {number}"}

        @self.app.get("/volume/{number:int}/paper/{pdf_name:str}", tags=["json"])
        async def volume_citation_paper_by_name(number: int, pdf_name: str):
            """
            Get paper citation
            """
            paper = self.getPaper(number, pdf_name)
            if paper:
                record = paper.getMergedDict()
                return record
            else:
                return {"error": f"unknown volume number {number} or paper {pdf_name}"}

        @self.app.get(
            "/volume/{number:int}/paper/{pdf_name:str}/citation", tags=["citation"]
        )
        async def volume_paper_citation(number: int, pdf_name: str):
            """
            Get paper citation
            """
            paper = self.getPaper(number, pdf_name)
            if paper:
                citation = BibTexConverter.convert_paper(paper)
                return PlainTextResponse(content=citation)
            else:
                return {"error": f"unknown volume number {number} or paper {pdf_name}"}

        @self.app.get("/Vol-{number:int}/{pdf_name}.yaml")
        async def paperYaml(number: int, pdf_name: str):
            paper = self.getPaper(number, pdf_name)
            paper_dict = paper.getMergedDict()
            yaml_content = yaml.dump(paper_dict)
            return Response(content=yaml_content, media_type="application/x-yaml")

        @self.app.get("/Vol-{number:int}.yaml")
        async def volumeYaml(number: int):
            vol = self.getVolume(number)
            if vol:
                volume_dict = vol.getMergedDict()
            else:
                volume_dict = {"error": f"unknown volume number {number}"}
            yaml_content = yaml.dump(volume_dict)
            return Response(content=yaml_content, media_type="application/x-yaml")

        @self.app.get("/volume/{number:int}/paper.yaml", tags=["yaml"])
        async def volume_papers_yaml(number: int):
            vol = self.getVolume(number)
            if vol:
                paper_records = [paper.getMergedDict() for paper in vol.papers]
            else:
                paper_records = {"error": f"unknown volume number {number}"}
            yaml_content = yaml.dump(paper_records)
            return Response(content=yaml_content, media_type="application/x-yaml")

        @self.app.get("/volume/{number:int}/paper/{pdf_name:str}.yaml", tags=["yaml"])
        async def volume_paper_yaml(number: int, pdf_name: str):
            paper = self.getPaper(number, pdf_name)
            if paper:
                paper_dict = paper.getMergedDict()
            else:
                paper_dict = {
                    "error": f"unknown volume number {number} or paper {pdf_name}"
                }
            yaml_content = yaml.dump(paper_dict)
            return Response(content=yaml_content, media_type="application/x-yaml")

    def volumeHtml(self, number: int, ext: str = ".pdf") -> HTMLResponse:
        """
        get html Response for the given volume by number
        Args:
            number: volume number
            ext: file extension
        """
        vol = self.getVolume(number)
        if vol:
            content = vol.getHtml(ext=ext, fixLinks=True)
            return HTMLResponse(content=content, status_code=200)
        else:
            content = vol.get_empty_volume_page()
            return HTMLResponse(content=content, status_code=200)

    def getVolume(self, number: int) -> Volume:
        """
        get the volume for the given number

        Args:
            number(int): the number of the volume to fetch

        Returns:
            Volume: the volume or None if the volume number is not known
        """
        vol = self.vm.getVolume(number)
        return vol

    def getPaper(
        self, number: int, pdf_name: str, exceptionOnFail: bool = True
    ) -> Paper:
        """
        get the paper for the given volume number and pdf_name

        Args:
            number(int): the number of the volume the paper is part of
            pdf_name(str): the pdf name of the paper
            exceptionOnFail(bool): if True raise an exception on failure

        Returns:
            Paper: the paper or None if the paper is not found
        """
        paper = self.pm.getPaper(number, pdf_name)
        if paper is None and exceptionOnFail:
            raise HTTPException(
                status_code=404, detail=f"paper Vol-{number}/{pdf_name}.pdf not found"
            )
        return paper

__init__(vm, pm, static_directory='static')

constructor

Parameters:

Name Type Description Default
vm(VolumeManager)

the volume manager to use

 required
pm(PaperManager)

the paper manager to use

 required
static_directory(str)

the directory for static html files to use

 required
Source code in ceurspt/webserver.py 
 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
    def __init__(
        self, vm: VolumeManager, pm: PaperManager, static_directory: str = "static"
    ):
        """
        constructor

        Args:
            vm(VolumeManager): the volume manager to use
            pm(PaperManager): the paper manager to use
            static_directory(str): the directory for static html files to use
        """
        self.app = FastAPI()
        # https://fastapi.tiangolo.com/tutorial/static-files/
        self.app.mount(
            "/static", StaticFiles(directory=static_directory), name="static"
        )
        self.vm = vm
        self.pm = pm

        @self.app.get("/index.html/{upper:int}/{lower:int}")
        async def index_html(upper: Optional[int], lower: Optional[int]):
            content = self.vm.index_html(upper=upper, lower=lower)
            return HTMLResponse(content)

        @self.app.get("/index.html")
        async def full_index_html():
            return await index_html(upper=None, lower=None)

        @self.app.get("/Vol-{number:int}/{pdf_name:str}.pdf")
        async def paperPdf(number: int, pdf_name: str):
            """
            get the PDF for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            pdf = paper.getPdf()
            return FileResponse(pdf)

        @self.app.get("/Vol-{number:int}/{pdf_name}.json")
        async def paperJson(number: int, pdf_name: str):
            """
            get the json response for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            paper_dict = paper.getMergedDict()
            return paper_dict

        @self.app.get("/Vol-{number:int}/{pdf_name}.wbjson")
        async def paperWikibaseCliJson(number: int, pdf_name: str):
            """
            get the json response to the wikibase-cli for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            paper_dict = paper.as_wb_dict()
            return paper_dict

        @self.app.get("/Vol-{number:int}/{pdf_name}/{qid}.wbcli")
        async def paperWikibaseCli(number: int, pdf_name, qid: str):
            """
            get the json response to the wikibase-cli for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            paper_cli_text = paper.as_wbi_cli_text(qid)
            return PlainTextResponse(paper_cli_text)

        @self.app.get("/Vol-{number:int}/{pdf_name}.html")
        async def paperHtml(number: int, pdf_name: str):
            """
            get the html response for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            content = paper.asHtml()
            return HTMLResponse(content=content)

        @self.app.get("/Vol-{number:int}/{pdf_name}.txt")
        async def paperText(number: int, pdf_name: str):
            """
            get the text for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            text = paper.getText()
            return PlainTextResponse(text)

        @self.app.get("/Vol-{number:int}/{pdf_name}.smw")
        async def paperSMW(number: int, pdf_name: str):
            """
            Get semantic media wiki markup of the given paper"""
            paper = self.getPaper(number, pdf_name)
            if paper:
                markup = paper.as_smw_markup()
            else:
                markup = f"""{{{{Paper
|id=Vol-{number}/{pdf_name}
|volume=Vol-{number}
}}}}"""
            return PlainTextResponse(markup)

        @self.app.get("/Vol-{number:int}/{pdf_name}.qs")
        async def paperQuickStatementns(number: int, pdf_name: str):
            """
            get the quickstatements for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            qs = paper.as_quickstatements()
            return PlainTextResponse(qs)

        @self.app.get("/Vol-{number:int}/{pdf_name}.grobid")
        async def paperGrobidXml(number: int, pdf_name: str):
            """
            get the grobid XML for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            xml = paper.getContentByPostfix(".tei.xml")
            return Response(content=xml, media_type="application/xml")

        @self.app.get("/Vol-{number:int}/{pdf_name}.cermine")
        async def paperCermineXml(number: int, pdf_name: str):
            """
            get the grobid XML for the given paper
            """
            paper = self.getPaper(number, pdf_name)
            xml = paper.getContentByPostfix(".cermine.xml")
            return Response(content=xml, media_type="application/xml")

        @self.app.get("/Vol-{number:int}.smw")
        async def volumeSMW(number: int):
            """
            Get semantic media wiki markup of volume by given id
            """
            vol = self.getVolume(number)
            if vol:
                markup = vol.as_smw_markup()
            else:
                markup = f"{{{{Volume|number={number}}}}}"
            return PlainTextResponse(markup)

        @self.app.get("/Vol-{number:int}.json")
        async def volumeJson(number: int):
            """
            Get metadata of volume by given id
            """
            vol = self.getVolume(number)
            if vol:
                return vol.getMergedDict()
            else:
                return {"error": f"unknown volume number {number}"}

        @self.app.get("/Vol-{number:int}")
        async def volumeHtmlWithPdf(number: int):
            """
            get html Response for the given volume by number
            displaying pdfs directly
            """
            return self.volumeHtml(number, ext=".pdf")

        @self.app.get("/Vol-{number:int}.html")
        async def volumeHtmlWithHtml(number: int):
            """
            get html Response for the given volume by number
            displaying pdfs embedded in html
            """
            return self.volumeHtml(number, ext=".html")

        @self.app.get("/")
        async def home():
            """
            Return the home
            """
            url = "https://github.com/ceurws/ceur-spt"
            response = RedirectResponse(url=url, status_code=302)
            return response

        @self.app.get("/volume/{number:int}", tags=["json"])
        async def volume_citation(number: int):
            """
            Get volume record
            """
            vol = self.getVolume(number)
            if vol:
                record = vol.getMergedDict()
                return record
            else:
                return {"error": f"unknown volume number {number}"}

        @self.app.get("/volume/{number:int}/paper", tags=["json"])
        async def volume_citation_paper_by_number(number: int):
            """
            Get volume papers
            """
            vol = self.getVolume(number)
            if vol:
                paper_records = []
                for paper in vol.papers:
                    paper_records.append(paper.getMergedDict())
                return paper_records
            else:
                return {"error": f"unknown volume number {number}"}

        @self.app.get("/volume/{number:int}/citation", tags=["citation"])
        async def volume_citation_citation(number: int):
            """
            Get volume citation
            """
            vol = self.getVolume(number)
            if vol:
                citation = BibTexConverter.convert_volume(vol)
                return PlainTextResponse(content=citation)
            else:
                return {"error": f"unknown volume number {number}"}

        @self.app.get("/volume/{number:int}/paper/{pdf_name:str}", tags=["json"])
        async def volume_citation_paper_by_name(number: int, pdf_name: str):
            """
            Get paper citation
            """
            paper = self.getPaper(number, pdf_name)
            if paper:
                record = paper.getMergedDict()
                return record
            else:
                return {"error": f"unknown volume number {number} or paper {pdf_name}"}

        @self.app.get(
            "/volume/{number:int}/paper/{pdf_name:str}/citation", tags=["citation"]
        )
        async def volume_paper_citation(number: int, pdf_name: str):
            """
            Get paper citation
            """
            paper = self.getPaper(number, pdf_name)
            if paper:
                citation = BibTexConverter.convert_paper(paper)
                return PlainTextResponse(content=citation)
            else:
                return {"error": f"unknown volume number {number} or paper {pdf_name}"}

        @self.app.get("/Vol-{number:int}/{pdf_name}.yaml")
        async def paperYaml(number: int, pdf_name: str):
            paper = self.getPaper(number, pdf_name)
            paper_dict = paper.getMergedDict()
            yaml_content = yaml.dump(paper_dict)
            return Response(content=yaml_content, media_type="application/x-yaml")

        @self.app.get("/Vol-{number:int}.yaml")
        async def volumeYaml(number: int):
            vol = self.getVolume(number)
            if vol:
                volume_dict = vol.getMergedDict()
            else:
                volume_dict = {"error": f"unknown volume number {number}"}
            yaml_content = yaml.dump(volume_dict)
            return Response(content=yaml_content, media_type="application/x-yaml")

        @self.app.get("/volume/{number:int}/paper.yaml", tags=["yaml"])
        async def volume_papers_yaml(number: int):
            vol = self.getVolume(number)
            if vol:
                paper_records = [paper.getMergedDict() for paper in vol.papers]
            else:
                paper_records = {"error": f"unknown volume number {number}"}
            yaml_content = yaml.dump(paper_records)
            return Response(content=yaml_content, media_type="application/x-yaml")

        @self.app.get("/volume/{number:int}/paper/{pdf_name:str}.yaml", tags=["yaml"])
        async def volume_paper_yaml(number: int, pdf_name: str):
            paper = self.getPaper(number, pdf_name)
            if paper:
                paper_dict = paper.getMergedDict()
            else:
                paper_dict = {
                    "error": f"unknown volume number {number} or paper {pdf_name}"
                }
            yaml_content = yaml.dump(paper_dict)
            return Response(content=yaml_content, media_type="application/x-yaml")

getPaper(number, pdf_name, exceptionOnFail=True)

get the paper for the given volume number and pdf_name

Parameters:

Name Type Description Default
number(int)

the number of the volume the paper is part of

 required
pdf_name(str)

the pdf name of the paper

 required
exceptionOnFail(bool)

if True raise an exception on failure

 required

Returns:

Name Type Description
Paper Paper

the paper or None if the paper is not found
Source code in ceurspt/webserver.py 
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
def getPaper(
    self, number: int, pdf_name: str, exceptionOnFail: bool = True
) -> Paper:
    """
    get the paper for the given volume number and pdf_name

    Args:
        number(int): the number of the volume the paper is part of
        pdf_name(str): the pdf name of the paper
        exceptionOnFail(bool): if True raise an exception on failure

    Returns:
        Paper: the paper or None if the paper is not found
    """
    paper = self.pm.getPaper(number, pdf_name)
    if paper is None and exceptionOnFail:
        raise HTTPException(
            status_code=404, detail=f"paper Vol-{number}/{pdf_name}.pdf not found"
        )
    return paper

getVolume(number)

get the volume for the given number

Parameters:

Name Type Description Default
number(int)

the number of the volume to fetch

 required

Returns:

Name Type Description
Volume Volume

the volume or None if the volume number is not known
Source code in ceurspt/webserver.py 
318
319
320
321
322
323
324
325
326
327
328
329
def getVolume(self, number: int) -> Volume:
    """
    get the volume for the given number

    Args:
        number(int): the number of the volume to fetch

    Returns:
        Volume: the volume or None if the volume number is not known
    """
    vol = self.vm.getVolume(number)
    return vol

volumeHtml(number, ext='.pdf')

get html Response for the given volume by number Args: number: volume number ext: file extension

Source code in ceurspt/webserver.py 
303
304
305
306
307
308
309
310
311
312
313
314
315
316
def volumeHtml(self, number: int, ext: str = ".pdf") -> HTMLResponse:
    """
    get html Response for the given volume by number
    Args:
        number: volume number
        ext: file extension
    """
    vol = self.getVolume(number)
    if vol:
        content = vol.getHtml(ext=ext, fixLinks=True)
        return HTMLResponse(content=content, status_code=200)
    else:
        content = vol.get_empty_volume_page()
        return HTMLResponse(content=content, status_code=200)