def test_fossey_schema():
data = {
"page": 405,
"number": 25728,
"suffix": "B",
"reference": "Mai: MDP, VI, 11.I, 11",
"newEdition": "Paulus AOAT 50, 981",
"secondaryLiterature": "NABU 1997/1",
"cdliNumber": "P123456",
"museumNumber": MuseumNumberSchema().dump(MuseumNumber.of("K.4562")),
"externalProject": "dcclt",
"notes": "Das Zeichen ist eigentlich ZA₇",
"date": "Marduk-apla-iddina I, 1171-1159 BC",
"transliteration": "me-luḫ-ḫa",
"sign":
"M15,21.7c-0.1-0.1-0.2-0.4-0.2-0.8c-0.1-1-0.1-1.2-0.5-1.3c-0.2",
}
fossey = Fossey(
405,
25728,
"B",
"Mai: MDP, VI, 11.I, 11",
"Paulus AOAT 50, 981",
"NABU 1997/1",
"P123456",
MuseumNumber.of("K.4562"),
"dcclt",
"Das Zeichen ist eigentlich ZA₇",
"Marduk-apla-iddina I, 1171-1159 BC",
"me-luḫ-ḫa",
"M15,21.7c-0.1-0.1-0.2-0.4-0.2-0.8c-0.1-1-0.1-1.2-0.5-1.3c-0.2",
)
assert FosseySchema().load(data) == fossey
assert FosseySchema().dump(fossey) == data
def query_transliterated_numbers(self):
cursor = self._fragments.find_many(
HAS_TRANSLITERATION, projection=["museumNumber"]
).sort("_id", pymongo.ASCENDING)
return MuseumNumberSchema(many=True).load(
fragment["museumNumber"] for fragment in cursor
)
def test_number_deserialization():
number = MuseumNumber.of("Z.1.b")
fragment = FragmentSchema().load({
**FragmentSchema().dump(LemmatizedFragmentFactory.build()),
"museumNumber":
MuseumNumberSchema().dump(number),
})
assert fragment.number == number
def query_transliterated_line_to_vec(self) -> List[LineToVecEntry]:
cursor = self._fragments.find_many(HAS_TRANSLITERATION, {"text": False})
return [
LineToVecEntry(
MuseumNumberSchema().load(fragment["museumNumber"]),
fragment["script"],
tuple(
LineToVecEncoding.from_list(line_to_vec)
for line_to_vec in fragment["lineToVec"]
),
)
for fragment in cursor
]
def test_number_serialization():
fragment = LemmatizedFragmentFactory.build()
data = FragmentSchema().dump(fragment)
assert data["museumNumber"] == MuseumNumberSchema().dump(fragment.number)
def test_dump():
assert MuseumNumberSchema().dump(MUSEUM_NUMBER) == SERIALIZED
def test_missing(property_):
data = {**SERIALIZED}
data.pop(property_)
assert MuseumNumberSchema().validate(data)
def test_invalid(property_, value):
assert MuseumNumberSchema().validate({**SERIALIZED, property_: value})
def test_load():
assert MuseumNumberSchema().load(SERIALIZED) == MUSEUM_NUMBER
def mongo_sign_si_2():
return {
"_id":
"SI_2",
"lists": [{
"name": "HZL",
"number": "13a"
}],
"unicode": [],
"notes": [],
"internalNotes": [],
"literature": [],
"values": [
{
"value": "Å¡i-2",
"subIndex": 2,
"questionable": False,
"deprecated": False,
"notes": [],
"internalNotes": [],
},
{
"value": "hu-2",
"questionable": False,
"deprecated": False,
"notes": [],
"internalNotes": [],
},
],
"forms": [],
"mesZl":
"""<div align="center">1 **AŠ** 𒀸</div>""",
"LaBaSi":
"12",
"logograms": [
{
"logogram":
"AÅ -IKU",
"atf":
"AÅ -IKU",
"wordId": ["ikû I"],
"schrammLogogramme":
"AŠ-IKU; *ikû* (ein Flächenmaß); ME 43 CD 126b ZL "
"290",
},
{
"logogram":
"<sup>mul</sup>AÅ -IKU",
"atf":
"{mul}AÅ -IKU",
"wordId": ["ikû I"],
"schrammLogogramme":
"<sup>mul</sup>AŠ-IKU; *ikû* (Sternbild Pegasus); "
"ME 43 CD 126b ZL 290",
},
],
"fossey": [{
"page":
405,
"number":
25728,
"suffix":
"B",
"reference":
"Mai: MDP, VI, 11.I, 11",
"newEdition":
"Paulus AOAT 50, 981",
"secondaryLiterature":
"NABU 1997/1",
"cdliNumber":
"P123456",
"museumNumber":
MuseumNumberSchema().dump(MuseumNumber.of("K.4562")),
"externalProject":
"dcclt",
"notes":
"Das Zeichen ist eigentlich ZA₇",
"date":
"Marduk-apla-iddina I, 1171-1159 BC",
"transliteration":
"me-luḫ-ḫa",
"sign":
"M15,21.7c-0.1-0.1-0.2-0.4-0.2-0.8c-0.1-1-0.1-1.2-0.5-1.3c-0.2",
}],
}
True,
Labels(
surface=SurfaceLabel.from_label(
atf.Surface.OBVERSE, [atf.Status.CORRECTION]
)
),
LineNumber(1),
True,
),
{
"type": "ParallelFragment",
"prefix": "//",
"content": [OneOfTokenSchema().dump(ValueToken.of("cf. F K.1 &d o! 1"))],
"displayValue": "cf. F K.1 &d o! 1",
"hasCf": True,
"museumNumber": MuseumNumberSchema().dump(MuseumNumber.of("K.1")),
"hasDuplicates": True,
"surface": {
"status": ["CORRECTION"],
"surface": "OBVERSE",
"abbreviation": "o",
"text": "",
},
"labels": {
"object": None,
"surface": {
"status": ["CORRECTION"],
"surface": "OBVERSE",
"abbreviation": "o",
"text": "",
},
def to_dict(chapter: Chapter, include_documents=False):
return {
"textId": {
"genre": chapter.text_id.genre.value,
"category": chapter.text_id.category,
"index": chapter.text_id.index,
},
"classification":
chapter.classification.value,
"stage":
chapter.stage.value,
"version":
chapter.version,
"name":
chapter.name,
"order":
chapter.order,
"signs":
list(chapter.signs),
"record":
RecordSchema().dump(chapter.record),
"parserVersion":
chapter.parser_version,
"manuscripts": [{
"id":
manuscript.id,
"siglumDisambiguator":
manuscript.siglum_disambiguator,
"museumNumber":
((str(manuscript.museum_number) if manuscript.museum_number else
"") if include_documents else manuscript.museum_number
and MuseumNumberSchema().dump(manuscript.museum_number)),
"accession":
manuscript.accession,
"periodModifier":
manuscript.period_modifier.value,
"period":
manuscript.period.long_name,
"provenance":
manuscript.provenance.long_name,
"type":
manuscript.type.long_name,
"notes":
manuscript.notes,
"colophon":
TextSchema().dump(manuscript.colophon),
"unplacedLines":
TextSchema().dump(manuscript.unplaced_lines),
"references": (ApiReferenceSchema if include_documents else
ReferenceSchema)().dump(manuscript.references,
many=True),
} for manuscript in chapter.manuscripts],
"uncertainFragments":
MuseumNumberSchema().dump(UNCERTAIN_FRAGMENTS, many=True),
"lines": [{
"number":
OneOfLineNumberSchema().dump(line.number),
"variants": [{
"reconstruction":
OneOfTokenSchema().dump(variant.reconstruction, many=True),
"note":
variant.note and NoteLineSchema().dump(variant.note),
"parallelLines":
ParallelLineSchema().dump(variant.parallel_lines, many=True),
"intertext":
OneOfNoteLinePartSchema().dump(variant.intertext, many=True),
"manuscripts": [{
"manuscriptId":
manuscript_line.manuscript_id,
"labels":
[label.to_value() for label in manuscript_line.labels],
"line":
OneOfLineSchema().dump(manuscript_line.line),
"paratext":
OneOfLineSchema().dump(manuscript_line.paratext,
many=True),
"omittedWords":
list(manuscript_line.omitted_words),
} for manuscript_line in variant.manuscripts],
} for variant in line.variants],
"isSecondLineOfParallelism":
line.is_second_line_of_parallelism,
"isBeginningOfSection":
line.is_beginning_of_section,
"translation":
TranslationLineSchema().dump(line.translation, many=True),
} for line in chapter.lines],
}
def museum_number_is(number: MuseumNumber) -> dict:
serialized = MuseumNumberSchema().dump(number)
return {f"museumNumber.{key}": value for key, value in serialized.items()}