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}}}"),
)
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}",
(
StringPart("this is a note "),
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]
"part,expected",
[
(StringPart(TEXT), StringPart(TEXT.title())),
(EmphasisPart(TEXT), EmphasisPart(TEXT.title())),
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,
), )
def ebl_atf_text_line__emphasis_part(self, text: str) -> EmphasisPart:
return EmphasisPart(text)
]),
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"), )), ))
]),
Text.of_iterable([
NoteLine((LanguagePart.of_transliteration(
Language.AKKADIAN,
(Word.of([Reading.of_name("bu")]), )), ))
]),
Text.of_iterable([
NoteLine((LanguagePart.of_transliteration(
Language.AKKADIAN,
),
(
SealDollarLine(1),
{
"type": "SealDollarLine",
"prefix": "$",
"content": [OneOfTokenSchema().dump(ValueToken.of(" seal 1"))],
"number": 1,
"displayValue": "seal 1",
},
),
(
NoteLine(
(
StringPart("a note "),
EmphasisPart("italic"),
LanguagePart.of_transliteration(
Language.AKKADIAN, [Word.of([Reading.of_name("bu")])]
),
BibliographyPart.of(BibliographyId("A"), "1-4"),
)
),
{
"type": "NoteLine",
"prefix": "#note: ",
"parts": [
{"type": "StringPart", "text": "a note "},
{"type": "EmphasisPart", "text": "italic"},
{
"type": "LanguagePart",
"language": Language.AKKADIAN.name,
def make_part(self, data, **kwargs) -> EmphasisPart:
return EmphasisPart(data["text"])