def test_updating_alignment(client, bibliography, sign_repository, signs,
text_repository):
allow_signs(signs, sign_repository)
chapter = ChapterFactory.build()
allow_references(chapter, bibliography)
text_repository.create_chapter(chapter)
alignment = 0
omitted_words = (1, )
updated_chapter = attr.evolve(
chapter,
lines=(attr.evolve(
chapter.lines[0],
variants=(attr.evolve(
chapter.lines[0].variants[0],
manuscripts=(attr.evolve(
chapter.lines[0].variants[0].manuscripts[0],
line=TextLine.of_iterable(
chapter.lines[0].variants[0].manuscripts[0].line.
line_number,
(Word.of(
[
Reading.of_name("ku"),
Joiner.hyphen(),
BrokenAway.open(),
Reading.of_name("nu"),
Joiner.hyphen(),
Reading.of_name("ši"),
BrokenAway.close(),
],
alignment=alignment,
variant=Word.of(
[Logogram.of_name("KU")],
language=Language.SUMERIAN,
),
), ),
),
omitted_words=omitted_words,
), ),
), ),
), ),
)
expected_chapter = ApiChapterSchema().dump(updated_chapter)
post_result = client.simulate_post(create_chapter_url(
chapter, "/alignment"),
body=json.dumps(DTO))
assert post_result.status == falcon.HTTP_OK
assert post_result.json == expected_chapter
get_result = client.simulate_get(create_chapter_url(chapter))
assert get_result.status == falcon.HTTP_OK
assert get_result.json == expected_chapter
def make_token(self, data, **kwargs):
return (
Logogram.of(
data["name_parts"],
data["sub_index"],
data["modifiers"],
data["flags"],
data["sign"],
data["surrogate"],
)
.set_enclosure_type(frozenset(data["enclosure_type"]))
.set_erasure(data["erasure"])
)
def test_logogram(
name_parts,
sub_index,
modifiers,
flags,
sign,
surrogate,
expected_value,
expected_clean_value,
expected_name,
) -> None:
logogram = Logogram.of(name_parts, sub_index, modifiers, flags, sign,
surrogate)
expected_parts = (*name_parts, sign) if sign else name_parts
assert logogram.value == expected_value
assert logogram.clean_value == expected_clean_value
assert (
logogram.get_key() ==
f"Logogram⁝{expected_value}⟨{'⁚'.join(token.get_key() for token in expected_parts)}⟩"
)
assert logogram.name_parts == name_parts
assert logogram.name == expected_name
assert logogram.modifiers == tuple(modifiers)
assert logogram.flags == tuple(flags)
assert logogram.lemmatizable is False
assert logogram.sign == sign
assert logogram.surrogate == tuple(surrogate)
serialized = {
"type": "Logogram",
"name": expected_name,
"nameParts": OneOfTokenSchema().dump(name_parts, many=True),
"subIndex": sub_index,
"modifiers": modifiers,
"flags": [flag.value for flag in flags],
"surrogate": OneOfTokenSchema().dump(surrogate, many=True),
"sign": sign and OneOfTokenSchema().dump(sign),
}
assert_token_serialization(logogram, serialized)
from ebl.transliteration.domain.word_tokens import Word
from ebl.fragmentarium.domain.joins import Join, Joins
COLLECTION = "fragments"
JOINS_COLLECTION = "joins"
ANOTHER_LEMMATIZED_FRAGMENT = attr.evolve(
TransliteratedFragmentFactory.build(),
text=Text(
(
TextLine(
LineNumber(1),
(
Word.of(
[Logogram.of_name("GI", 6)], unique_lemma=(WordId("ginâ I"),)
),
Word.of([Reading.of_name("ana")], unique_lemma=(WordId("ana II"),)),
Word.of([Reading.of_name("ana")], unique_lemma=(WordId("ana II"),)),
Word.of(
[
Reading.of_name("u", 4),
Joiner.hyphen(),
Reading.of_name("šu"),
],
unique_lemma=(WordId("ūsu I"),),
),
AkkadianWord.of(
[ValueToken.of("ana")], unique_lemma=(WordId("normalized I"),)
),
),
def ebl_atf_text_line__surrogate(
self, name, sub_index, modifiers, flags, surrogate
):
return Logogram.of(
tuple(name.children), sub_index, modifiers, flags, None, surrogate.children
)
def ebl_atf_text_line__logogram(self, name, sub_index, modifiers, flags, sign=None):
return Logogram.of(tuple(name.children), sub_index, modifiers, flags, sign)
class LemmatizedFragmentFactory(TransliteratedFragmentFactory):
text = Text((
TextLine.of_iterable(
LineNumber(1, True),
(
Word.of([UnidentifiedSign.of()]),
Word.of([
Logogram.of_name(
"BA",
surrogate=[
Reading.of_name("ku"),
Joiner.hyphen(),
Reading.of_name("u", 4),
],
)
]),
Column.of(),
Tabulation.of(),
Word.of([
BrokenAway.open(),
UnknownNumberOfSigns.of(),
Joiner.hyphen(),
Reading.of_name("ku"),
BrokenAway.close(),
Joiner.hyphen(),
Reading.of_name("nu"),
Joiner.hyphen(),
Reading.of_name("ši"),
]),
Variant.of(Divider.of(":"), Reading.of_name("ku")),
Word.of([
BrokenAway.open(),
UnknownNumberOfSigns.of(),
BrokenAway.close(),
]),
Column.of(2),
Divider.of(":", ("@v", ), (Flag.DAMAGE, )),
CommentaryProtocol.of("!qt"),
Word.of([Number.of_name("10", flags=[Flag.DAMAGE])]),
),
),
TextLine.of_iterable(
LineNumber(2, True),
(
Word.of([BrokenAway.open(),
UnknownNumberOfSigns.of()]),
Word.of([Logogram.of_name("GI", 6)],
unique_lemma=(WordId("ginâ I"), )),
Word.of([Reading.of_name("ana")],
unique_lemma=(WordId("ana I"), )),
Word.of(
[
Reading.of_name("u₄"),
Joiner.hyphen(),
Reading.of_name("š[u"),
],
unique_lemma=(WordId("ūsu I"), ),
),
Word.of([UnknownNumberOfSigns.of(),
BrokenAway.close()]),
),
),
TextLine.of_iterable(
LineNumber(3, True),
(
Word.of([BrokenAway.open(),
UnknownNumberOfSigns.of()]),
Word.of(
unique_lemma=(WordId("kīdu I"), ),
parts=[
Reading.of((
ValueToken.of("k"),
BrokenAway.close(),
ValueToken.of("i"),
)),
Joiner.hyphen(),
Reading.of_name("du"),
],
),
Word.of(unique_lemma=(WordId("u I"), ),
parts=[Reading.of_name("u")]),
Word.of(
unique_lemma=(WordId("bamātu I"), ),
parts=[
Reading.of_name("ba"),
Joiner.hyphen(),
Reading.of_name("ma"),
Joiner.hyphen(),
Reading.of((
ValueToken.of("t"),
BrokenAway.open(),
ValueToken.of("i"),
)),
],
),
Word.of([UnknownNumberOfSigns.of(),
BrokenAway.close()]),
),
),
TextLine.of_iterable(
LineNumber(6, True),
(
Word.of([
BrokenAway.open(),
UnknownNumberOfSigns.of(),
BrokenAway.close(),
]),
Word.of([UnclearSign.of([Flag.DAMAGE])]),
Word.of(unique_lemma=(WordId("mu I"), ),
parts=[Reading.of_name("mu")]),
Word.of(
unique_lemma=(WordId("tamalāku I"), ),
parts=[
Reading.of_name("ta"),
Joiner.hyphen(),
Reading.of_name("ma"),
InWordNewline.of(),
Joiner.hyphen(),
Reading.of_name("tu", 2),
],
),
),
),
TextLine.of_iterable(
LineNumber(7, True),
(
Word.of([
Variant.of(Reading.of_name("šu"),
CompoundGrapheme.of(["BI×IS"]))
]),
LanguageShift.normalized_akkadian(),
AkkadianWord.of([ValueToken.of("kur")],
unique_lemma=(WordId("normalized I"), )),
),
),
StateDollarLine(
atf.Qualification.AT_LEAST,
1,
ScopeContainer(atf.Surface.OBVERSE, ""),
atf.State.MISSING,
None,
),
ImageDollarLine("1", None, "numbered diagram of triangle"),
RulingDollarLine(atf.Ruling.SINGLE),
LooseDollarLine("this is a loose line"),
SealDollarLine(1),
SealAtLine(1),
HeadingAtLine(1),
ColumnAtLine(ColumnLabel([atf.Status.COLLATION], 1)),
SurfaceAtLine(
SurfaceLabel([atf.Status.COLLATION], atf.Surface.SURFACE,
"stone wig")),
ObjectAtLine(
ObjectLabel([atf.Status.COLLATION], atf.Object.OBJECT,
"stone wig")),
DiscourseAtLine(atf.Discourse.DATE),
DivisionAtLine("paragraph", 5),
CompositeAtLine(atf.Composite.DIV, "part", 1),
NoteLine((
StringPart("a note "),
EmphasisPart("italic"),
LanguagePart.of_transliteration(
Language.AKKADIAN, (Word.of([Reading.of_name("bu")]), )),
)),
ParallelComposition(False, "my name", LineNumber(1)),
ParallelText(
True,
TextId(CorpusGenre.LITERATURE, 1, 1),
ChapterName(Stage.OLD_BABYLONIAN, "", "my name"),
LineNumber(1),
False,
),
ParallelFragment(False, MuseumNumber.of("K.1"), True, Labels(),
LineNumber(1), False),
))
class TransliteratedFragmentFactory(FragmentFactory):
text = Text((
TextLine.of_iterable(
LineNumber(1, True),
(
Word.of([UnidentifiedSign.of()]),
Word.of([
Logogram.of_name(
"BA",
surrogate=[
Reading.of_name("ku"),
Joiner.hyphen(),
Reading.of_name("u", 4),
],
)
]),
Column.of(),
Tabulation.of(),
Word.of([
BrokenAway.open(),
UnknownNumberOfSigns.of(),
Joiner.hyphen(),
Reading.of_name("ku"),
BrokenAway.close(),
Joiner.hyphen(),
Reading.of_name("nu"),
Joiner.hyphen(),
Reading.of_name("ši"),
]),
Variant.of(Divider.of(":"), Reading.of_name("ku")),
Word.of([
BrokenAway.open(),
UnknownNumberOfSigns.of(),
BrokenAway.close(),
]),
Column.of(2),
Divider.of(":", ("@v", ), (Flag.DAMAGE, )),
CommentaryProtocol.of("!qt"),
Word.of([Number.of_name("10", flags=[Flag.DAMAGE])]),
),
),
TextLine.of_iterable(
LineNumber(2, True),
(
Word.of([
BrokenAway.open(),
UnknownNumberOfSigns.of(),
BrokenAway.close(),
]),
Word.of([Logogram.of_name("GI", 6)]),
Word.of([Reading.of_name("ana")]),
Word.of([
Reading.of_name("u", 4),
Joiner.hyphen(),
Reading.of((
ValueToken.of("š"),
BrokenAway.open(),
ValueToken.of("u"),
)),
]),
Word.of([UnknownNumberOfSigns.of(),
BrokenAway.close()]),
),
),
TextLine.of_iterable(
LineNumber(3, True),
(
Word.of([BrokenAway.open(),
UnknownNumberOfSigns.of()]),
Word.of([
Reading.of((
ValueToken.of("k"),
BrokenAway.close(),
ValueToken.of("i"),
)),
Joiner.hyphen(),
Reading.of_name("du"),
]),
Word.of([Reading.of_name("u")]),
Word.of([
Reading.of_name("ba"),
Joiner.hyphen(),
Reading.of_name("ma"),
Joiner.hyphen(),
Reading.of((
ValueToken.of("t"),
BrokenAway.open(),
ValueToken.of("i"),
)),
]),
Word.of([UnknownNumberOfSigns.of(),
BrokenAway.close()]),
),
),
TextLine.of_iterable(
LineNumber(6, True),
(
Word.of([
BrokenAway.open(),
UnknownNumberOfSigns.of(),
BrokenAway.close(),
]),
Word.of([UnclearSign.of([Flag.DAMAGE])]),
Word.of([Reading.of_name("mu")]),
Word.of([
Reading.of_name("ta"),
Joiner.hyphen(),
Reading.of_name("ma"),
InWordNewline.of(),
Joiner.hyphen(),
Reading.of_name("tu", 2),
]),
),
),
TextLine.of_iterable(
LineNumber(7, True),
(
Word.of([
Variant.of(Reading.of_name("šu"),
CompoundGrapheme.of(["BI×IS"]))
]),
LanguageShift.normalized_akkadian(),
AkkadianWord.of([ValueToken.of("kur")]),
),
),
StateDollarLine(
atf.Qualification.AT_LEAST,
1,
ScopeContainer(atf.Surface.OBVERSE, ""),
atf.State.MISSING,
None,
),
ImageDollarLine("1", None, "numbered diagram of triangle"),
RulingDollarLine(atf.Ruling.SINGLE),
LooseDollarLine("this is a loose line"),
SealDollarLine(1),
SealAtLine(1),
HeadingAtLine(1),
ColumnAtLine(ColumnLabel([atf.Status.COLLATION], 1)),
SurfaceAtLine(
SurfaceLabel([atf.Status.COLLATION], atf.Surface.SURFACE,
"stone wig")),
ObjectAtLine(
ObjectLabel([atf.Status.COLLATION], atf.Object.OBJECT,
"stone wig")),
DiscourseAtLine(atf.Discourse.DATE),
DivisionAtLine("paragraph", 5),
CompositeAtLine(atf.Composite.DIV, "part", 1),
NoteLine((
StringPart("a note "),
EmphasisPart("italic"),
LanguagePart.of_transliteration(
Language.AKKADIAN, (Word.of([Reading.of_name("bu")]), )),
)),
ParallelComposition(False, "my name", LineNumber(1)),
ParallelText(
True,
TextId(CorpusGenre.LITERATURE, 1, 1),
ChapterName(Stage.OLD_BABYLONIAN, "", "my name"),
LineNumber(1),
False,
),
ParallelFragment(False, MuseumNumber.of("K.1"), True, Labels(),
LineNumber(1), False),
))
signs = (
"X BA KU ABZ075 ABZ207a\\u002F207b\\u0020X ABZ377n1/KU ABZ377n1 ABZ411\n"
"MI DIŠ UD ŠU\n"
"KI DU ABZ411 BA MA TI\n"
"X MU TA MA UD\n"
"ŠU/|BI×IS|")
folios = Folios((Folio("WGL", "3"), Folio("XXX", "3")))
record = Record((RecordEntry("test", RecordType.TRANSLITERATION), ))
line_to_vec = ((
LineToVecEncoding.TEXT_LINE,
LineToVecEncoding.TEXT_LINE,
LineToVecEncoding.TEXT_LINE,
LineToVecEncoding.TEXT_LINE,
LineToVecEncoding.TEXT_LINE,
LineToVecEncoding.SINGLE_RULING,
), )
Joiner.hyphen(),
Reading.of_name("bu"),
])
],
ErasureState.NONE,
), ),
),
],
),
(
"1. KIMIN {u₂#}[...] {u₂#} [...]",
[
TextLine.of_iterable(
LineNumber(1),
(
Word.of([Logogram.of_name("KIMIN")]),
Word.of(parts=[
Determinative.of([
Reading.of_name(
"u", 2, flags=[atf.Flag.DAMAGE])
]),
BrokenAway.open(),
UnknownNumberOfSigns.of(),
BrokenAway.close(),
]),
LoneDeterminative.of_value(
[
Determinative.of([
Reading.of_name(
"u", 2, flags=[atf.Flag.DAMAGE])
])
from ebl.transliteration.domain.line_number import LineNumber
from ebl.transliteration.domain.normalized_akkadian import AkkadianWord
from ebl.transliteration.domain.sign_tokens import Logogram, Reading
from ebl.transliteration.domain.text import Text
from ebl.transliteration.domain.text_line import TextLine
from ebl.transliteration.domain.tokens import ErasureState, Joiner, ValueToken
from ebl.transliteration.domain.word_tokens import Word
COLLECTION = "fragments"
ANOTHER_LEMMATIZED_FRAGMENT = attr.evolve(
TransliteratedFragmentFactory.build(),
text=Text((TextLine(
LineNumber(1),
(
Word.of([Logogram.of_name("GI", 6)],
unique_lemma=(WordId("ginâ I"), )),
Word.of([Reading.of_name("ana")],
unique_lemma=(WordId("ana II"), )),
Word.of([Reading.of_name("ana")],
unique_lemma=(WordId("ana II"), )),
Word.of(
[
Reading.of_name("u", 4),
Joiner.hyphen(),
Reading.of_name("šu"),
],
unique_lemma=(WordId("ūsu I"), ),
),
AkkadianWord.of([ValueToken.of("ana")],
unique_lemma=(WordId("normalized I"), )),
"1]2",
Word.of([
Number.of((ValueToken.of("1"), BrokenAway.close(),
ValueToken.of("2")))
]),
),
(
"1[2",
Word.of([
Number.of((ValueToken.of("1"), BrokenAway.open(),
ValueToken.of("2")))
]),
),
("ʾ", Word.of([Reading.of_name("ʾ")])),
("du₁₁", Word.of([Reading.of_name("du", 11)])),
("GAL", Word.of([Logogram.of_name("GAL")])),
(
"kur(GAL)",
Word.of(
[Reading.of_name("kur", sign=Grapheme.of(SignName("GAL")))]),
),
(
"KUR(GAL)",
Word.of(
[Logogram.of_name("KUR", sign=Grapheme.of(SignName("GAL")))]),
),
(
"kur(|GAL|)",
Word.of(
[Reading.of_name("kur", sign=CompoundGrapheme.of(["GAL"]))]),
),