def _get_symbol_data(arxiv_id: ArxivId, stdout: str) -> List[EquationSymbols]:
symbol_data = []
for result in stdout.strip().splitlines():
data = json.loads(result)
symbols = None
if data["success"] is True:
mathml = data["mathMl"]
symbols = parse_equation(mathml)
symbol_data.append(
EquationSymbols(
arxiv_id=arxiv_id,
success=data["success"],
equation_index=int(data["i"]),
tex_path=data["tex_path"],
equation=data["equation"],
equation_start=int(data["equation_start"]),
equation_depth=int(data["equation_depth"]),
context_tex=data["context_tex"],
error_message=data["errorMessage"],
symbols=symbols,
))
return symbol_data
def test_parse_equation():
with open(
get_test_path(os.path.join("mathml", "x_sub_t_sub_i.xml"))
) as mathml_file:
mathml = mathml_file.read()
symbols = parse_equation(mathml)
assert len(symbols) == 5
x_sub_t_sub_i = list(
filter(lambda s: "msub" in str(s.element) and "x" in str(s.element), symbols)
)[0]
t_sub_i = list(
filter(lambda s: "msub" in str(s.element) and s is not x_sub_t_sub_i, symbols)
)[0]
x = list(filter(lambda s: str(s.element) == "<mi>x</mi>", symbols))[0]
t = list(filter(lambda s: str(s.element) == "<mi>t</mi>", symbols))[0]
i = list(filter(lambda s: str(s.element) == "<mi>i</mi>", symbols))[0]
assert len(x_sub_t_sub_i.children) == 2
assert x in x_sub_t_sub_i.children
assert t_sub_i in x_sub_t_sub_i.children
assert len(t_sub_i.children) == 2
assert t in t_sub_i.children
assert i in t_sub_i.children
def _get_symbol_data(arxiv_id: ArxivId, stdout: str) -> Iterator[SymbolData]:
for result in stdout.strip().splitlines():
data = json.loads(result)
symbols = None
if data["success"] is True:
mathml = data["mathMl"]
symbols = parse_equation(mathml)
yield SymbolData(
arxiv_id=arxiv_id,
success=data["success"],
equation_index=int(data["i"]),
tex_path=data["tex_path"],
equation=data["equation"],
equation_start=int(data["equation_start"]),
equation_depth=int(data["equation_depth"]),
context_tex=data["context_tex"],
errorMessage=data["errorMessage"],
symbols=symbols,
)