Skip to content

Use MathicsScanner tables for render LaTeX #1644

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mmatera merged 2 commits into from
Jan 24, 2026
Merged

Use MathicsScanner tables for render LaTeX #1644

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
227173c
Use MathicsScanner tables for render LaTeX
mmatera Jan 24, 2026
e5833f3
Handle text-mode character in operators. Handle . add tests.
mmatera Jan 24, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions admin-tools/make-JSON-tables.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,8 @@ PYTHON=${PYTHON:-python}

cd $mydir/../mathics/data
mathics3-generate-json-table \
--field=latex-named-characters \
--field=unicode-to-latex \
--field=ascii-operator-to-symbol \
--field=ascii-operator-to-unicode \
--field=ascii-operator-to-wl-unicode \
Expand Down
24 changes: 14 additions & 10 deletions mathics/core/convert/op.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,10 +29,12 @@
unicode_operator_to_ascii = {
val: operator_to_ascii[key] for key, val in operator_to_unicode.items()
}
unicode_to_amslatex = OPERATOR_CONVERSION_TABLES["unicode-to-amslatex"]

UNICODE_TO_AMSLATEX = OPERATOR_CONVERSION_TABLES["unicode-to-amslatex"]
UNICODE_TO_LATEX = OPERATOR_CONVERSION_TABLES["unicode-to-latex"]

amstex_operators = {

AMSTEX_OPERATORS = {
"\u2032": "'",
"\u2032\u2032": "''",
"\u2062": " ",
Expand Down Expand Up @@ -92,7 +94,7 @@ def hex_form_code(char_str):
return hex(ord(char_str))[2:]

for candidate_dict in (
unicode_to_amslatex,
UNICODE_TO_AMSLATEX,
# amstex_operators,
unicode_operator_to_ascii,
):
Expand All @@ -106,10 +108,12 @@ def hex_form_code(char_str):
# if it is already an ascii, return without changes.
if unicode_op.isascii():
return unicode_op

# the `unicode_op` cannot be converted into an ascii string. Show a
# warning and return a `\symbol{code}` expression.
logging.warning(
"Unicode op" + unicode_op + "(" + hex_form_code(unicode_op) + ") not found."
)
return '\\symbol{"' + hex_form_code(unicode_op) + "}"
try:
return r"\text{" + UNICODE_TO_LATEX[unicode_op] + "}"
except KeyError:
# the `unicode_op` cannot be converted into an ascii string. Show a
# warning and return a `\symbol{code}` expression.
logging.warning(
"Unicode op" + unicode_op + "(" + hex_form_code(unicode_op) + ") not found."
)
return '\\symbol{"' + hex_form_code(unicode_op) + "}"
51 changes: 34 additions & 17 deletions mathics/format/render/latex.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,12 @@
)
from mathics.builtin.colors.color_directives import RGBColor
from mathics.core.atoms import String
from mathics.core.convert.op import amstex_operators, get_latex_operator
from mathics.core.convert.op import (
AMSTEX_OPERATORS,
UNICODE_TO_AMSLATEX,
UNICODE_TO_LATEX,
get_latex_operator,
)
from mathics.core.exceptions import BoxConstructError
from mathics.core.formatter import (
add_conversion_fn,
Expand All @@ -57,26 +62,38 @@
"^": r"{}^{\wedge}",
"~": r"\sim{}",
"|": r"\vert{}",
"\u222b": r"\int ",
"\u2146": r"\, d",
"\uF74C": r"\, d",
"\U0001D451": r"\, d",
"\u00d7": r"\times ",
}
TEX_TEXT_REPLACE = TEX_REPLACE.copy()
TEX_TEXT_REPLACE = {
r"{": r"\{",
r"}": r"\}",
r"_": r"\_",
"<": r"$<$",
">": r"$>$",
"~": r"$\sim$",
"|": r"$\vert$",
"\\": r"$\backslash$",
"^": r"${}^{\wedge}$",
}

TEX_REPLACE.update(UNICODE_TO_AMSLATEX)
TEX_REPLACE.update(
{
key: r"\text{" + val + "}"
for key, val in UNICODE_TO_LATEX.items()
if key not in TEX_REPLACE
}
)

TEX_TEXT_REPLACE.update(UNICODE_TO_LATEX)
TEX_TEXT_REPLACE.update(
{
"<": r"$<$",
">": r"$>$",
"~": r"$\sim$",
"|": r"$\vert$",
"\\": r"$\backslash$",
"^": r"${}^{\wedge}$",
"\u222b": r"$\int$ ",
"\uF74C": r"\, d",
"\u00d7": r"$\times$",
key: f"${val}$"
for key, val in UNICODE_TO_AMSLATEX.items()
if key not in TEX_TEXT_REPLACE
}
)


TEX_REPLACE_RE = re.compile("([" + "".join([re.escape(c) for c in TEX_REPLACE]) + "])")


Expand Down Expand Up @@ -117,7 +134,7 @@ def render(format, string, in_text=False):
return render("%s", text)
else:
# First consider the special cases
op_string = amstex_operators.get(text, None)
op_string = AMSTEX_OPERATORS.get(text, None)
if op_string:
return op_string

Expand Down
18 changes: 9 additions & 9 deletions test/format/format_tests.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,10 +64,10 @@
'"\[Pi] is a trascendental number"':
msg: A String
latex:
System`InputForm: "\\text{``\u03C0 is a trascendental number''}"
System`OutputForm: "\\text{\u03C0 is a trascendental number}"
System`StandardForm: "\\text{\u03C0 is a trascendental number}"
System`TraditionalForm: "\\text{\u03C0 is a trascendental number}"
System`InputForm: "\\text{``$\\pi$ is a trascendental number''}"
System`OutputForm: "\\text{$\\pi$ is a trascendental number}"
System`StandardForm: "\\text{$\\pi$ is a trascendental number}"
System`TraditionalForm: "\\text{$\\pi$ is a trascendental number}"
mathml:
System`InputForm: "<ms>\u03C0&nbsp;is&nbsp;a&nbsp;trascendental&nbsp;number</ms>"
System`OutputForm: "<mtext>\u03C0&nbsp;is&nbsp;a&nbsp;trascendental&nbsp;number</mtext>"
Expand Down Expand Up @@ -455,12 +455,12 @@ Graphics[{}]:
"Grid[{{\"Spanish\", \"Hola!\"},{\"Portuguese\", \"Ol\xE0!\"},{\"English\", \"Hi!\"}}]":
msg: Strings in a GridBox
latex:
System`InputForm: \text{Grid[\{\{"Spanish", "Hola!"\}, \{"Portuguese", "Olà!"\}, \{"English", "Hi!"\}\}]}
System`InputForm: \text{Grid[\{\{"Spanish", "Hola!"\}, \{"Portuguese", "Ol\`{a}!"\}, \{"English", "Hi!"\}\}]}
System`OutputForm: '\text{Spanish Hola!\newline

\newline

Portuguese Olà!\newline
Portuguese Ol\`{a}!\newline

\newline

Expand All @@ -469,9 +469,9 @@ Graphics[{}]:
}
'
System`StandardForm: "\\begin{array}{cc} \\text{Spanish} & \\text{Hola!}\\\\ \\\
text{Portuguese} & \\text{Ol\xE0!}\\\\ \\text{English} & \\text{Hi!}\\end{array}"
text{Portuguese} & \\text{Ol\\`{a}!}\\\\ \\text{English} & \\text{Hi!}\\end{array}"
System`TraditionalForm: "\\begin{array}{cc} \\text{Spanish} & \\text{Hola!}\\\\\
\ \\text{Portuguese} & \\text{Ol\xE0!}\\\\ \\text{English} & \\text{Hi!}\\end{array}"
\ \\text{Portuguese} & \\text{Ol\\`{a}!}\\\\ \\text{English} & \\text{Hi!}\\end{array}"
mathml:
System`InputForm: "<mtext>Grid[{{&quot;Spanish&quot;,&nbsp;&quot;Hola!&quot;},&nbsp;{&quot;Portuguese&quot;,&nbsp;&quot;Olà!&quot;},&nbsp;{&quot;English&quot;,&nbsp;&quot;Hi!&quot;}}]</mtext>"
System`OutputForm: '<mtext>Spanish&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Hola!</mtext><mtext></mtext><mtext>Portuguese&nbsp;&nbsp;&nbsp;Olà!</mtext><mtext></mtext><mtext>English&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Hi!</mtext><mtext></mtext>'
Expand Down Expand Up @@ -800,7 +800,7 @@ TableForm[{{a,b},{c,d}}]:
msg: A greek letter symbol
latex:
System`InputForm: \alpha
System`OutputForm: \text{α}
System`OutputForm: \text{$\alpha$}
System`StandardForm: \alpha
System`TraditionalForm: \alpha
mathml:
Expand Down
18 changes: 18 additions & 0 deletions test/format/test_latex.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,8 @@ def get_latex(wl_expression):
@pytest.mark.parametrize(
("testcase", "expected"),
[
("_", r"\_"),
('"_"', r"\text{\_}"),
('"["', r"\text{[}"),
('"]"', r"\text{]}"),
("HoldForm[A[[1,2]]]", r"A\left[\left[1, 2\right]\right]"),
Expand All @@ -31,6 +33,22 @@ def get_latex(wl_expression):
("CupCap[c,b]", r"c \stackrel{\smile}{\frown} b"),
("Congruent[c,b]", r"c \equiv b"),
("Pi", r"\pi"),
# In symbols and expressions
(r"\[Alpha]", r"\alpha"),
# In this case, without the linebreak, the tokeniser
# produce an error...
("\\[Alpha]s\n", r"\text{$\alpha$s}"),
(r"\[Alpha] s", r"s \alpha"),
(r"\[AAcute]", r"\text{\'{a}}"),
# In this case, without the linebreak, the tokeniser
# produce an error...
("\\[AAcute]s\n", r"\text{\'{a}s}"),
(r"\[AAcute] s", r"s \text{\'{a}}"),
# In strings
(r'"\[Alpha]"', r"\text{$\alpha$}"),
(r'"\[Alpha]s"', r"\text{$\alpha$s}"),
(r'"\[AAcute]"', r"\text{\'{a}}"),
(r'"M\[AAcute]s!"', r"\text{M\'{a}s!}"),
],
)
def test_expressions(testcase, expected):
Expand Down
Loading