def test_issue_no21(self):
# test for https://github.com/phfaist/pylatexenc/issues/21
def capitalize_acronyms(s, pos):
if s[pos] in ('{', '}'):
# preserve existing braces
return (1, s[pos])
m = re.compile(r'\b[A-Z]{2,}\w*\b').match(s, pos)
if m is None:
return None
return (m.end() - m.start(), "{" + m.group() + "}")
u = UnicodeToLatexEncoder(conversion_rules=[
latexencode.UnicodeToLatexConversionRule(latexencode.RULE_CALLABLE,
capitalize_acronyms),
] + latexencode.get_builtin_conversion_rules('defaults'))
input = "Title with {Some} ABC acronyms LIKe this."
self.assertEqual(u.unicode_to_latex(input),
"Title with {Some} {ABC} acronyms {LIKe} this.")
u = UnicodeToLatexEncoder(conversion_rules=[
latexencode.UnicodeToLatexConversionRule(
latexencode.RULE_REGEX,
[
(re.compile(r'([{}])'), r'\1'), # keep existing braces
(re.compile(r'\b([A-Z]{2,}\w*)\b'), r'{\1}'),
]),
] + latexencode.get_builtin_conversion_rules('defaults'))
input = "Title with {Some} ABC acronyms LIKe this."
self.assertEqual(u.unicode_to_latex(input),
"Title with {Some} {ABC} acronyms {LIKe} this.")
def test_rules_01(self):
def acallable(s, pos):
if s[pos] == "\N{LATIN SMALL LETTER E WITH ACUTE}":
return (1, r"{\'{e}}")
if s.startswith('...', pos):
return (3, r"\ldots")
return None
u = UnicodeToLatexEncoder(conversion_rules=[
latexencode.UnicodeToLatexConversionRule(
latexencode.RULE_DICT, {
ord("\N{LATIN CAPITAL LETTER A WITH GRAVE}"): r"{{\`{A}}}",
ord("%"): r"\textpercent",
}),
latexencode.UnicodeToLatexConversionRule(latexencode.RULE_REGEX, [
(re.compile('v(otre)'), r'n\1'),
(re.compile("s'exclama", flags=re.I), r"s'exprima"),
(re.compile('\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}'),
r"{\^i}"),
]),
'unicode-xml', # expand built-in rule names
latexencode.UnicodeToLatexConversionRule(latexencode.RULE_CALLABLE,
acallable),
])
input = "\"\N{LATIN CAPITAL LETTER A WITH GRAVE} votre sant\N{LATIN SMALL LETTER E WITH ACUTE}!\" s'exclama le ma\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}tre de maison ... \N{LATIN SMALL LETTER A WITH GRAVE} 100%."
self.assertEqual(
u.unicode_to_latex(input),
"\"{{\\`{A}}} notre sant\\'{e}!\" s'exprima le ma{\\^i}tre de maison {\\ldots} \\`{a} 100{\\textpercent}."
)
def test_custom_conversion_rules(self):
u = latexencode.PartialLatexToLatexEncoder(conversion_rules=[
latexencode.UnicodeToLatexConversionRule(
latexencode.RULE_REGEX,
[
# this rule should never kick in because braces are
# preserved as keep_latex_chars
(re.compile(r'([{}])'), r'BRACE<\1>'),
# other replacement rules
(re.compile(r'\b([A-Z]{2,}\w*)\b'), r'{\1}'),
]),
'defaults',
])
input = r"Title with {Some} ABC àcr\^onyms LIKe this."
self.assertEqual(u.unicode_to_latex(input),
r"Title with {Some} {ABC} \`acr\^onyms {LIKe} this.")
