def test_constructor_sets_correct_fields():
assert CHAPTER.text_id == TextId(GENRE, CATEGORY, INDEX)
assert CHAPTER.classification == CLASSIFICATION
assert CHAPTER.stage == STAGE
assert CHAPTER.version == VERSION
assert CHAPTER.name == CHAPTER_NAME
assert CHAPTER.order == ORDER
assert CHAPTER.uncertain_fragments == (MUSEUM_NUMBER, )
assert CHAPTER.manuscripts[0].id == MANUSCRIPT_ID
assert CHAPTER.manuscripts[0].siglum == Siglum(PROVENANCE, PERIOD, TYPE,
SIGLUM_DISAMBIGUATOR)
assert CHAPTER.manuscripts[0].siglum_disambiguator == SIGLUM_DISAMBIGUATOR
assert CHAPTER.manuscripts[0].museum_number == MUSEUM_NUMBER
assert CHAPTER.manuscripts[0].accession == ACCESSION
assert CHAPTER.manuscripts[0].period_modifier == PERIOD_MODIFIER
assert CHAPTER.manuscripts[0].period == PERIOD
assert CHAPTER.manuscripts[0].provenance == PROVENANCE
assert CHAPTER.manuscripts[0].type == TYPE
assert CHAPTER.manuscripts[0].notes == NOTES
assert CHAPTER.manuscripts[0].colophon == COLOPHON
assert CHAPTER.manuscripts[0].unplaced_lines == UNPLACED_LINES
assert CHAPTER.manuscripts[0].references == REFERENCES
assert CHAPTER.lines[0].number == LINE_NUMBER
assert CHAPTER.lines[0].variants == (LINE_VARIANT_1, )
assert (CHAPTER.lines[0].is_second_line_of_parallelism ==
IS_SECOND_LINE_OF_PARALLELISM)
assert CHAPTER.lines[0].is_beginning_of_section == IS_BEGINNING_OF_SECTION
assert CHAPTER.lines[0].translation == TRANSLATION
assert CHAPTER.signs == SIGNS
assert CHAPTER.record == RECORD
def test_invalid_extent() -> None:
with pytest.raises(ValueError):
Chapter(
TextId(GENRE, 0, 0),
manuscripts=(Manuscript(MANUSCRIPT_ID), ),
lines=(Line(
LineNumber(1),
(LINE_VARIANT_1, ),
translation=(TranslationLine(tuple(),
extent=Extent(LineNumber(2))), ),
), ),
)
def test_parallel_text(cf, chapter, display_value) -> None:
text_id = TextId(Genre.LITERATURE, 1, 1)
line_number = LineNumber(1)
line = ParallelText(cf, text_id, chapter, line_number)
assert line.has_cf is cf
assert line.text == text_id
assert line.chapter == chapter
assert line.line_number == line_number
assert line.display_value == display_value
assert line.atf == Atf(f"// {display_value}")
assert line.lemmatization == (LemmatizationToken(display_value), )
def test_text_constructor_sets_correct_fields() -> None:
assert TEXT.id == TextId(GENRE, CATEGORY, INDEX)
assert TEXT.genre == GENRE
assert TEXT.category == CATEGORY
assert TEXT.index == INDEX
assert TEXT.name == NAME
assert TEXT.has_doi == HAS_DOI
assert TEXT.number_of_verses == VERSES
assert TEXT.approximate_verses == APPROXIMATE
assert TEXT.intro == INTRO
assert TEXT.chapters[0].stage == STAGE
assert TEXT.chapters[0].name == CHAPTER_NAME
assert TEXT.chapters[0].translation == TRANSLATION
assert TEXT.chapters[0].uncertain_fragments == UNCERTAIN_FRAGMENTS
def test_overlapping_languages() -> None:
Chapter(
TextId(GENRE, 0, 0),
manuscripts=(Manuscript(MANUSCRIPT_ID), ),
lines=(
Line(
LineNumber(1),
(LINE_VARIANT_1, ),
translation=(TranslationLine(tuple(), "en",
Extent(LineNumber(2))), ),
),
Line(
LineNumber(2),
(LINE_VARIANT_2, ),
translation=(TranslationLine(tuple(), "de"), ),
),
),
)
def test_extant_lines_schema() -> None:
manuscript = Manuscript(1)
manuscript_line = ManuscriptLine(1, LABELS, MANUSCRIPT_TEXT_1)
variant = LineVariant(tuple(), manuscripts=(manuscript_line, ))
text_line = Line(LineNumber(1), (variant, ))
chapter = Chapter(TextId(Genre.LITERATURE, 0, 0),
manuscripts=(manuscript, ),
lines=(text_line, ))
assert ExtantLinesSchema().dump(chapter) == {
"extantLines": {
str(manuscript.siglum): {
" ".join(label.to_value() for label in manuscript_line.labels):
[{
"isSideBoundary": False,
"lineNumber":
OneOfLineNumberSchema().dump(text_line.number),
}]
}
}
}
import pytest
from ebl.transliteration.domain.text_id import TextId
from ebl.transliteration.domain.genre import Genre
@pytest.mark.parametrize(
"text_id,expected",
[
(TextId(Genre.LITERATURE, 0, 0), "L 0.0"),
(TextId(Genre.LEXICOGRAPHY, 5, 8), "Lex V.8"),
(TextId(Genre.MEDICINE, 1, 3), "Med I.3"),
],
)
def test_str(text_id, expected) -> None:
assert str(text_id) == expected
def test_find_raises_exception_if_text_not_found(text_repository) -> None:
with pytest.raises(NotFoundError):
text_repository.find(TextId(Genre.LITERATURE, 1, 1))
def id(self) -> TextId:
return TextId(self.genre, self.category, self.index)
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,
), )
"surface": {
"status": ["CORRECTION"],
"surface": "OBVERSE",
"abbreviation": "o",
"text": "",
},
"column": None,
},
"lineNumber": OneOfLineNumberSchema().dump(LineNumber(1)),
"exists": True,
},
),
(
ParallelText(
True,
TextId(Genre.LITERATURE, 1, 1),
ChapterName(Stage.OLD_BABYLONIAN, "version", "name"),
LineNumber(1),
True,
ChapterName(Stage.OLD_BABYLONIAN, "implicit", "name"),
),
{
"type": "ParallelText",
"prefix": "//",
"content": [
OneOfTokenSchema().dump(
ValueToken.of('cf. L I.1 OB "version" "name" 1')
)
],
"displayValue": 'cf. L I.1 OB "version" "name" 1',
"hasCf": True,
MANUSCRIPT_TEXT_3 = attr.evolve(MANUSCRIPT_TEXT_1, line_number=LineNumber(3))
LINE_VARIANT_3 = LineVariant(
LINE_RECONSTRUCTION,
None,
(ManuscriptLine(MANUSCRIPT_ID, tuple(), MANUSCRIPT_TEXT_3), ),
)
LINE_3 = Line(LineNumber(3), (LINE_VARIANT_3, ))
RECORD = Record(
(Author("Author", "Test", AuthorRole.EDITOR, ""), ),
(Translator("Author", "Test", "", "en"), ),
"",
)
TEXT_ID = TextId(GENRE, CATEGORY, INDEX)
CHAPTER = Chapter(
TEXT_ID,
CLASSIFICATION,
STAGE,
VERSION,
CHAPTER_NAME,
ORDER,
(Manuscript(
MANUSCRIPT_ID,
SIGLUM_DISAMBIGUATOR,
MUSEUM_NUMBER,
ACCESSION,
PERIOD_MODIFIER,
PERIOD,
PROVENANCE,
[atf.Status.CORRECTION]),
ColumnLabel.from_int(3, [atf.Status.UNCERTAIN]),
),
LineNumber(1),
),
),
(
"// F K.1 1",
ParallelFragment(False, MuseumNumber.of("K.1"), False, Labels(),
LineNumber(1)),
),
(
'// cf. L I.1 OB "my name" 1',
ParallelText(
True,
TextId(Genre.LITERATURE, 1, 1),
ChapterName(Stage.OLD_BABYLONIAN, "", "my name"),
LineNumber(1),
),
),
(
'// cf. L I.1 OB "my version" "my name" 1',
ParallelText(
True,
TextId(Genre.LITERATURE, 1, 1),
ChapterName(Stage.OLD_BABYLONIAN, "my version", "my name"),
LineNumber(1),
),
),
(
"// L I.1 1",
def ebl_atf_text_line__text_id(self, genre, category, number) -> TextId:
return TextId(
Genre(genre),
0 if category == "0" else roman.fromRoman(category),
int(number),
)
def make_id(self, data, **kwargs) -> TextId:
return TextId(data["genre"], data["category"], data["index"])
Line(
LineNumber(1),
(LineVariant(
(Caesura.certain(), ),
None,
(MANUSCRIPT_LINE.update_alignments([None]), ),
), ),
),
),
],
)
def test_merge_line(old: Line, new: Line, expected: Line) -> None:
assert old.merge(new) == expected
TEXT_ID = TextId(Genre.LITERATURE, 0, 0)
CLASSIFICATION = Classification.ANCIENT
STAGE = Stage.NEO_BABYLONIAN
VERSION = "A"
CHAPTER_NAME = "I"
ORDER = 1
MANUSCRIPT = Manuscript(MANUSCRIPT_ID)
MUSEUM_NUMBER = MuseumNumber.of("K.1")
CHAPTER = Chapter(
TEXT_ID,
CLASSIFICATION,
STAGE,
VERSION,
CHAPTER_NAME,
ORDER,
(MANUSCRIPT, ),