def test_note_line():
parts = (
StringPart("this is a note "),
EmphasisPart("italic text"),
LanguagePart.of_transliteration(Language.AKKADIAN, TRANSLITERATION),
LanguagePart.of_transliteration(Language.SUMERIAN, TRANSLITERATION),
LanguagePart.of_transliteration(Language.EMESAL, TRANSLITERATION),
)
line = NoteLine(parts)
assert line.parts == (
StringPart("this is a note "),
EmphasisPart("italic text"),
LanguagePart(Language.AKKADIAN,
expected_transliteration(Language.AKKADIAN)),
LanguagePart(Language.SUMERIAN,
expected_transliteration(Language.SUMERIAN)),
LanguagePart(Language.EMESAL,
expected_transliteration(Language.EMESAL)),
)
assert line.atf == (
"#note: this is a note "
"@i{italic text}"
f"@akk{{{EXPECTED_ATF}}}@sux{{{EXPECTED_ATF}}}@es{{{EXPECTED_ATF}}}")
assert line.lemmatization == (
LemmatizationToken("this is a note "),
LemmatizationToken("@i{italic text}"),
LemmatizationToken(f"@akk{{{EXPECTED_ATF}}}"),
LemmatizationToken(f"@sux{{{EXPECTED_ATF}}}"),
LemmatizationToken(f"@es{{{EXPECTED_ATF}}}"),
)
class ManuscriptLineFactory(factory.Factory):
class Meta:
model = ManuscriptLine
manuscript_id = factory.Sequence(lambda n: n)
labels = (
SurfaceLabel.from_label(Surface.OBVERSE),
ColumnLabel.from_label("iii", [Status.COLLATION, Status.CORRECTION]),
)
line = factory.Sequence(
lambda n: TextLine.of_iterable(
LineNumber(n),
(
Word.of(
[
Reading.of_name("ku"),
Joiner.hyphen(),
BrokenAway.open(),
Reading.of_name("nu"),
Joiner.hyphen(),
Reading.of_name("ši"),
BrokenAway.close(),
]
),
),
)
)
paratext = (NoteLine((StringPart("note"),)), RulingDollarLine(Ruling.SINGLE))
omitted_words = (1,)
class ChapterListingFactory(factory.Factory):
class Meta:
model = ChapterListing
stage = factory.fuzzy.FuzzyChoice(Stage)
name = factory.Faker("sentence")
translation = (TranslationLine((StringPart("foo"),), "en", None),)
uncertain_fragments = tuple()
def test_line_display_of_line() -> None:
translation_lines = (
TranslationLine((StringPart("bar"),), "de", None),
TranslationLine((StringPart("foo"),), DEFAULT_LANGUAGE, None),
)
line = LineFactory.build(translation=translation_lines)
line_display = LineDisplay.of_line(line)
assert line_display == LineDisplay(
line.number,
line.is_second_line_of_parallelism,
line.is_beginning_of_section,
line.variants[0].intertext,
line.variants[0].reconstruction,
translation_lines,
line.variants[0].note,
line.variants[0].parallel_lines,
)
assert line_display.title == make_title(translation_lines)
class LineVariantFactory(factory.Factory):
class Meta:
model = LineVariant
class Params:
manuscript_id = factory.Sequence(lambda n: n)
manuscript = factory.SubFactory(
ManuscriptLineFactory,
manuscript_id=factory.SelfAttribute("..manuscript_id"),
)
reconstruction = (
LanguageShift.normalized_akkadian(),
AkkadianWord.of((ValueToken.of("buāru"),)),
MetricalFootSeparator.uncertain(),
BrokenAway.open(),
UnknownNumberOfSigns.of(),
Caesura.certain(),
AkkadianWord.of(
(
UnknownNumberOfSigns.of(),
BrokenAway.close(),
Joiner.hyphen(),
ValueToken.of("buāru"),
),
(Flag.DAMAGE,),
),
)
note = factory.fuzzy.FuzzyChoice([None, NoteLine((StringPart("a note"),))])
manuscripts = factory.List([factory.SelfAttribute("..manuscript")], TupleFactory)
intertext = factory.fuzzy.FuzzyChoice([tuple(), (StringPart("bar"),)])
parallel_lines = factory.List(
[
factory.SubFactory(ParallelCompositionFactory),
factory.SubFactory(ParallelTextFactory),
factory.SubFactory(ParallelFragmentFactory),
],
TupleFactory,
)
class LineFactory(factory.Factory):
class Meta:
model = Line
class Params:
manuscript_id = factory.Sequence(lambda n: n)
variant = factory.SubFactory(
LineVariantFactory, manuscript_id=factory.SelfAttribute("..manuscript_id")
)
number = factory.Sequence(lambda n: LineNumber(n))
variants = factory.List([factory.SelfAttribute("..variant")], TupleFactory)
is_second_line_of_parallelism = factory.Faker("boolean")
is_beginning_of_section = factory.Faker("boolean")
translation = (TranslationLine((StringPart("foo"),), "en", None),)
PERIOD_MODIFIER = PeriodModifier.LATE
PERIOD = Period.OLD_BABYLONIAN
PROVENANCE = Provenance.NINEVEH
TYPE = ManuscriptType.LIBRARY
NOTES = "some notes"
COLOPHON = Transliteration.of_iterable(
[TextLine(LineNumber(1, True), (Word.of([Reading.of_name("ku")]), ))])
UNPLACED_LINES = Transliteration.of_iterable(
[TextLine(LineNumber(4, True), (Word.of([Reading.of_name("bu")]), ))])
REFERENCES = (ReferenceFactory.build(), )
LINE_NUMBER = LineNumber(1)
LINE_RECONSTRUCTION = (AkkadianWord.of((ValueToken.of("buāru"), )), )
IS_SECOND_LINE_OF_PARALLELISM = True
IS_BEGINNING_OF_SECTION = True
LABELS = (SurfaceLabel.from_label(Surface.OBVERSE), )
PARATEXT = (NoteLine((StringPart("note"), )), RulingDollarLine(Ruling.SINGLE))
OMITTED_WORDS = (1, )
NOTE = None
PARALLEL_LINES = (ParallelComposition(False, "a composition", LineNumber(7)), )
TRANSLATION = (TranslationLine((StringPart("foo"), ), "en", None), )
SIGNS = ("FOO BAR", )
MANUSCRIPT_TEXT_1 = TextLine(LineNumber(1),
(Word.of([Reading.of([ValueToken.of("ku")])]), ))
LINE_VARIANT_1 = LineVariant(
LINE_RECONSTRUCTION,
NOTE,
(ManuscriptLine(MANUSCRIPT_ID, LABELS, MANUSCRIPT_TEXT_1, PARATEXT,
OMITTED_WORDS), ),
def ebl_atf_text_line__string_part(self, text: str) -> StringPart:
return StringPart(text)
from ebl.transliteration.domain.markup import StringPart
from ebl.transliteration.domain.translation_line import TranslationLine
GENRE = Genre.LITERATURE
CATEGORY = 1
INDEX = 2
NAME = "Palm & Vine"
HAS_DOI = True
VERSES = 100
APPROXIMATE = True
CLASSIFICATION = Classification.ANCIENT
STAGE = Stage.NEO_BABYLONIAN
INTRO = "**Intro**"
CHAPTER_NAME = "I"
TRANSLATION = (
TranslationLine([StringPart("not the title")], "de"),
TranslationLine([StringPart("the title,")], "en"),
)
UNCERTAIN_FRAGMENTS = (UncertainFragment(MuseumNumber("X", "1"), True), )
CHAPTER = ChapterListing(STAGE, CHAPTER_NAME, TRANSLATION, UNCERTAIN_FRAGMENTS)
TEXT = Text(GENRE, CATEGORY, INDEX, NAME, HAS_DOI, VERSES, APPROXIMATE, INTRO,
(CHAPTER, ))
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
from ebl.transliteration.domain.text_line_transformer import TextLineTransformer
def parse_text(atf: str):
tree = LINE_PARSER.parse(atf, start="ebl_atf_text_line__text")
return TextLineTransformer().transform(tree)
def expected_language_part(language: Language, transliteration: str) -> LanguagePart:
return LanguagePart.of_transliteration(language, parse_text(transliteration))
@pytest.mark.parametrize( # pyre-ignore[56]
"atf,expected",
[
("this is a note ", (StringPart("this is a note "),)),
("@i{italic text}", (EmphasisPart("italic text"),)),
("@akk{{d}kur}", (expected_language_part(Language.AKKADIAN, "{d}kur"),)),
("@sux{kur}", (expected_language_part(Language.SUMERIAN, "kur"),)),
("@es{kur}", (expected_language_part(Language.EMESAL, "kur"),)),
(
"@bib{RN123@x 2-3a}",
(BibliographyPart.of(BibliographyId("RN123"), "x 2-3a"),),
),
("@bib{RN1\\}@2}", (BibliographyPart.of(BibliographyId("RN1}"), "2"),)),
("@bib{RN1@1\\}2}", (BibliographyPart.of(BibliographyId("RN1"), "1}2"),)),
("@bib{RN12\\@3@3}", (BibliographyPart.of(BibliographyId("RN12@3"), "3"),)),
("@bib{RN@1\\}\\@2}", (BibliographyPart.of(BibliographyId("RN"), "1}@2"),)),
(
"this is a note @i{italic text}@akk{kur}@sux{kur}",
(
[
(EmptyLine(), False),
(TextLine(LineNumber(2)), False),
(TextLine(LineNumber(1)), True),
],
)
def test_is_beginning_of_side(line, is_beginning) -> None:
line = ManuscriptLineFactory.build(line=line)
assert line.is_beginning_of_side is is_beginning
@pytest.mark.parametrize( # pyre-ignore[56]
"paratext,is_end",
[
(tuple(), False),
((NoteLine((StringPart("note"), )), ), False),
((StateDollarLine(None, atf.Extent.SEVERAL, None, None,
None), ), False),
((StateDollarLine(None, atf.Extent.END_OF, None, None, None), ), True),
(
(
StateDollarLine(None, atf.Extent.SEVERAL, None, None, None),
StateDollarLine(None, atf.Extent.END_OF, None, None, None),
),
True,
),
],
)
def test_is_end_of_side(paratext, is_end) -> None:
line = ManuscriptLineFactory.build(line=EmptyLine(), paratext=paratext)
assert line.is_end_of_side is is_end
(
"@prism!",
[
ObjectAtLine(
ObjectLabel([atf.Status.CORRECTION], atf.Object.PRISM))
],
),
("@prism", [ObjectAtLine(ObjectLabel([], atf.Object.PRISM))]),
("@object stone",
[ObjectAtLine(ObjectLabel([], atf.Object.OBJECT, "stone"))]),
("@fragment 1",
[ObjectAtLine(ObjectLabel([], atf.Object.FRAGMENT, "1"))]),
("@edge a", [SurfaceAtLine(SurfaceLabel([], atf.Surface.EDGE, "a"))]),
("@face a", [SurfaceAtLine(SurfaceLabel([], atf.Surface.FACE, "a"))]),
("@h1", [HeadingAtLine(1, tuple())]),
("@h1 foo", [HeadingAtLine(1, (StringPart("foo"), ))]),
("@column 1", [ColumnAtLine(ColumnLabel.from_int(1))]),
(
"@column 1!",
[ColumnAtLine(ColumnLabel.from_int(1, (atf.Status.CORRECTION, )))],
),
(
"@column 1!*",
[
ColumnAtLine(
ColumnLabel.from_int(
1, (atf.Status.CORRECTION, atf.Status.COLLATION)))
],
),
("@date", [DiscourseAtLine(atf.Discourse.DATE)]),
],
import pytest
from ebl.transliteration.domain.lark_parser import parse_translation_line
from ebl.transliteration.domain.markup import StringPart
from ebl.transliteration.domain.translation_line import Extent, TranslationLine
from ebl.transliteration.domain.labels import ColumnLabel, SurfaceLabel
from ebl.transliteration.domain.line_number import LineNumber
from ebl.transliteration.domain.atf import Surface
@pytest.mark.parametrize(
"atf,expected_line",
[
("#tr: translation", TranslationLine((StringPart("translation"),), "en", None)),
(
"#tr.en: translation",
TranslationLine((StringPart("translation"),), "en", None),
),
(
"#tr.ar.(2): translation",
TranslationLine(
(StringPart("translation"),), "ar", Extent(LineNumber(2), tuple())
),
),
(
"#tr.(2): translation",
TranslationLine(
(StringPart("translation"),), "en", Extent(LineNumber(2), tuple())
),
),
(
Line(
LineNumber(1),
(LineVariant(RECONSTRUCTION, NOTE, tuple()), ),
IS_SECOND_LINE_OF_PARALLELISM,
IS_BEGINNING_OF_SECTION,
),
Line(LineNumber(1),
(LineVariant(RECONSTRUCTION, NOTE, tuple()), ), True, True),
Line(LineNumber(1),
(LineVariant(RECONSTRUCTION, NOTE, tuple()), ), True, True),
),
(
Line(
LineNumber(1),
(LineVariant(RECONSTRUCTION, NoteLine(
(StringPart("a note"), )), tuple()), ),
IS_SECOND_LINE_OF_PARALLELISM,
IS_BEGINNING_OF_SECTION,
),
Line(
LineNumber(1),
(LineVariant(RECONSTRUCTION,
NoteLine((StringPart("new note"), )), tuple()), ),
IS_SECOND_LINE_OF_PARALLELISM,
IS_BEGINNING_OF_SECTION,
),
Line(
LineNumber(1),
(LineVariant(RECONSTRUCTION,
NoteLine((StringPart("new note"), )), tuple()), ),
IS_SECOND_LINE_OF_PARALLELISM,
import pytest
from ebl.lemmatization.domain.lemmatization import LemmatizationToken
from ebl.transliteration.domain.atf import Atf, Surface
from ebl.transliteration.domain.labels import ColumnLabel, SurfaceLabel
from ebl.transliteration.domain.line_number import LineNumber
from ebl.transliteration.domain.markup import StringPart
from ebl.transliteration.domain.translation_line import Extent, TranslationLine
@pytest.mark.parametrize( # pyre-ignore[56]
"parts,language,extent,prefix,translation",
[
((StringPart("foo"), StringPart("bar")), "en", None, "#tr.en",
"foobar"),
((StringPart("foo"), ), "de", Extent(
LineNumber(1)), "#tr.de.(1)", "foo"),
(
(StringPart("foo"), ),
"de",
Extent(
LineNumber(1),
(SurfaceLabel(tuple(), Surface.OBVERSE), ColumnLabel(
tuple(), 2)),
),
"#tr.de.(o ii 1)",
"foo",
),
],
)
def test_parallel_fragment(parts, language, extent, prefix,
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,
), )
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),
))
from ebl.transliteration.domain.markup import StringPart
from ebl.transliteration.domain.parallel_line import ParallelComposition
from ebl.transliteration.domain.translation_line import TranslationLine
REFERENCES = (ReferenceFactory.build(with_document=True), )
MANUSCRIPT = ManuscriptFactory.build(references=REFERENCES)
UNCERTAIN_FRAGMENTS = (MuseumNumber.of("K.1"), )
FIRST_MANUSCRIPT_LINE = ManuscriptLineFactory.build(
manuscript_id=MANUSCRIPT.id)
SECOND_MANUSCRIPT_LINE = ManuscriptLineFactory.build(
manuscript_id=MANUSCRIPT.id)
LINE_VARIANT = LineVariantFactory.build(
manuscripts=(FIRST_MANUSCRIPT_LINE, SECOND_MANUSCRIPT_LINE),
parallel_lines=(ParallelComposition(False, "name", LineNumber(2)), ),
intertext=(StringPart("bar"), ),
)
TRANSLATION_LINE = TranslationLine((StringPart("foo"), ), "en", None)
LINE = LineFactory.build(variants=(LINE_VARIANT, ),
translation=(TRANSLATION_LINE, ))
CHAPTER = ChapterFactory.build(manuscripts=(MANUSCRIPT, ),
uncertain_fragments=UNCERTAIN_FRAGMENTS,
lines=(LINE, ))
def strip_documents(chapter: Chapter) -> Chapter:
return attr.evolve(
chapter,
manuscripts=tuple(
attr.evolve(
manuscript,
from ebl.transliteration.domain.at_line import (
DiscourseAtLine,
SurfaceAtLine,
ColumnAtLine,
ObjectAtLine,
CompositeAtLine,
HeadingAtLine,
)
from ebl.transliteration.domain.labels import SurfaceLabel, ColumnLabel, ObjectLabel
from ebl.transliteration.domain.markup import StringPart
from ebl.transliteration.domain.atf import Atf
@pytest.mark.parametrize( # pyre-ignore[56]
"parts,parts_text", [(tuple(), ""),
((StringPart("a"), StringPart("b c")), " ab c")])
def test_at_line_heading(parts, parts_text) -> None:
at_line = HeadingAtLine(1, parts)
assert at_line.atf == Atf(f"@h1{parts_text}")
assert at_line.lemmatization == (LemmatizationToken(f"h1{parts_text}"), )
assert at_line.display_value == f"h1{parts_text}"
def test_at_line_column() -> None:
at_line = ColumnAtLine(ColumnLabel.from_int(1, (atf.Status.COLLATION, )))
assert at_line.lemmatization == (LemmatizationToken("column 1*"), )
assert at_line.display_value == "column 1*"
"displayValue": "seal 1",
},
),
(
HeadingAtLine(1),
{
"prefix": "@",
"content": [OneOfTokenSchema().dump(ValueToken.of("h1"))],
"type": "HeadingAtLine",
"number": 1,
"displayValue": "h1",
"parts": [],
},
),
(
HeadingAtLine(2, (StringPart("foo"),)),
{
"prefix": "@",
"content": [OneOfTokenSchema().dump(ValueToken.of("h2 foo"))],
"type": "HeadingAtLine",
"number": 2,
"displayValue": "h2 foo",
"parts": [{"type": "StringPart", "text": "foo"}],
},
),
(
StateDollarLine(
atf.Qualification.AT_LEAST,
atf.Extent.BEGINNING_OF,
ScopeContainer(atf.Surface.OBVERSE),
atf.State.BLANK,
PUNCTUATION = ";,:.-–—"
TEXT = "sed nec tortor varius, iaculis."
LANGUAGE_PART = LanguagePart(
Language.AKKADIAN,
[Reading.of_name("kur"), Divider.of(":")])
BIBLIOGRAPHY_PART = BibliographyPart(
Reference(BibliographyId("1"), ReferenceType.DISCUSSION,
TEXT + PUNCTUATION))
@pytest.mark.parametrize( # pyre-ignore[56]
"part,expected",
[
(
StringPart(f"{PUNCTUATION}A{PUNCTUATION}A{PUNCTUATION}"),
StringPart(f"{PUNCTUATION}A{PUNCTUATION}A"),
),
(
EmphasisPart(f"{PUNCTUATION}A{PUNCTUATION}A{PUNCTUATION}"),
EmphasisPart(f"{PUNCTUATION}A{PUNCTUATION}A"),
),
(LANGUAGE_PART, LANGUAGE_PART),
(BIBLIOGRAPHY_PART, BIBLIOGRAPHY_PART),
],
)
def test_part_rstrip(part: MarkupPart, expected: MarkupPart) -> None:
assert part.rstrip() == expected
@pytest.mark.parametrize( # pyre-ignore[56]
(
Text.of_iterable([
TextLine.of_iterable(LineNumber(1),
[Word.of([Reading.of_name("bu")])])
]),
Text.of_iterable([
TextLine.of_iterable(LineNumber(1),
[Word.of([Reading.of_name("bu")])])
]),
Text.of_iterable([
TextLine.of_iterable(LineNumber(1),
[Word.of([Reading.of_name("bu")])])
]),
),
(
Text.of_iterable([NoteLine((StringPart("this is a note "), ))]),
Text.of_iterable(
[NoteLine((StringPart("this is another note "), ))]),
Text.of_iterable(
[NoteLine((StringPart("this is another note "), ))]),
),
(
Text.of_iterable([NoteLine((StringPart("this is a note "), ))]),
Text.of_iterable([NoteLine((EmphasisPart("this is a note "), ))]),
Text.of_iterable([NoteLine((EmphasisPart("this is a note "), ))]),
),
(
Text.of_iterable([
NoteLine((LanguagePart.of_transliteration(
Language.AKKADIAN, (ValueToken.of("bu"), )), ))
]),
def test_make_title() -> None:
assert make_title(TRANSLATION) == (StringPart("The Title"),)
def make_part(self, data, **kwargs) -> StringPart:
return StringPart(data["text"])
