How to use the pylatexenc.latexwalker.LatexCharsNode function in pylatexenc
To help you get started, we’ve selected a few pylatexenc examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
phfaist / pylatexenc / test / test_latexwalker.py View on Github 
chars='\n\nAlso a ',
pos=27+1+26+19, len=2+7),
LatexMacroNode(parsing_state=parsing_state,
macroname=r'itshape',
macro_post_space='',
nodeargd=macrospec.ParsedMacroArgs(argspec='',argnlist=[]),
pos=27+1+26+20+1+7, len=15-7),
LatexCommentNode(parsing_state=parsing_state,
comment=' comment after a macro',
comment_post_space='\n',
pos=27+1+26+20+1+15, len=39-15),
LatexCommentNode(parsing_state=parsing_state,
comment=' and also a second line',
comment_post_space='\n',
pos=27+1+26+20+1+39, len=25),
LatexCharsNode(parsing_state=parsing_state,
chars='some italic text.',
pos=27+1+26+20+1+39+25, len=17),
],
0,len(latextext))
)\end{enumerate}
Indeed thanks to \cite[Lemma 3]{Author}, we know that...
'''
lw = LatexWalker(latextext, tolerant_parsing=False)
parsing_state = lw.make_parsing_state()
p = latextext.find(r'\textbf')+len(r'\textbf')
self.assertEqual(lw.get_latex_maybe_optional_arg(pos=p, parsing_state=parsing_state), None)
p = latextext.find(r'\cite')+len(r'\cite')
self.assertEqual(lw.get_latex_maybe_optional_arg(pos=p, parsing_state=parsing_state),
(LatexGroupNode(
parsing_state=parsing_state,
delimiters=('[', ']'),
nodelist=[
LatexCharsNode(
parsing_state=parsing_state,
chars='Lemma 3',
pos=p+1,
len=len('Lemma 3'),
)
],
pos=p,
len=9
),p,9,))
\item Hi there! % here goes a comment
\item[a] Hello! @@@
\end{enumerate}
Indeed thanks to \cite[Lemma 3]{Author}, we know that...
Also: {\itshape some italic text}.
'''
lw = LatexWalker(latextext, tolerant_parsing=False)
parsing_state = lw.make_parsing_state()
p = latextext.find(r'\begin{enumerate}')
good_parsed_structure = \
(LatexEnvironmentNode(
parsing_state=parsing_state,
environmentname='enumerate',
nodelist=[
LatexCharsNode(parsing_state=parsing_state,
chars='\n',
pos=p+22, len=1),
LatexMacroNode(parsing_state=parsing_state,
macroname='item',
nodeargd=macrospec.ParsedMacroArgs(argspec='[', argnlist=[None]),
macro_post_space=' ',
pos=p+23, len=6),
LatexCharsNode(parsing_state=parsing_state,
chars='Hi there! ',
pos=p+23+6, len=17-6),
LatexCommentNode(parsing_state=parsing_state,
comment=' here goes a comment',
comment_post_space='\n ',
pos=p+23+17, len=38-17+2),
LatexMacroNode(
parsing_state=parsing_state,LatexMacroNode(parsing_state=parsing_state, pos=20, len=40,
macroname='verb',
macro_post_space='',
nodeargd=macrospec.ParsedVerbatimArgs(
verbatim_chars_node=
LatexCharsNode(parsing_state=parsing_state, pos=26, len=33,
chars='\\begin{verbatim}...\\end{verbatim}'),
verbatim_delimiters=('+', '+'),
)),
LatexCharsNode(parsing_state=parsing_state, pos=60, len=4, chars=' to\n'),
LatexEnvironmentNode(
parsing_state=parsing_state, pos=64, len=91,
environmentname='verbatim', nodelist=[],
nodeargd=macrospec.ParsedVerbatimArgs(
verbatim_chars_node=
LatexCharsNode(
parsing_state=parsing_state, pos=80, len=61,
chars='\ntypeset \\verbatim text with \\LaTeX $ escapes \\(like this\\).\n'
),
verbatim_delimiters=None,
)
),
LatexCharsNode(parsing_state=parsing_state, pos=155, len=12,
chars='\nThis is it.')
],
0,
167)
)chars='and ',
pos=p, len=4),
LatexMacroNode(parsing_state=parsing_state,
macroname='textbf',
nodeargd=macrospec.ParsedMacroArgs(argspec='{', argnlist=[
LatexGroupNode(parsing_state=parsing_state,
delimiters=('{', '}'),
nodelist=[
LatexCharsNode(parsing_state=parsing_state,
chars='bold text',
pos=p+54-42, len=9)
],
pos=p+53-42, len=11)
]),
pos=p+46-42, len=64-46),
LatexCharsNode(parsing_state=parsing_state,
chars=' and ',
pos=p+64-42, len=69-64),
LatexMathNode(parsing_state=parsing_state,
displaytype='inline',
delimiters=('$', '$'),
nodelist=[
LatexMacroNode(parsing_state=parsing_state_inner,
macroname='vec',
macro_post_space=' ',
nodeargd=macrospec.ParsedMacroArgs(argspec='{', argnlist=[
LatexCharsNode(parsing_state=parsing_state_inner,
chars='b',
pos=p+75-42, len=1)
]),
pos=p+70-42, len=76-70),
],chars='Indeed thanks to ',
pos=0,len=17),
LatexMacroNode(
parsing_state=parsing_state2,
macroname='cite',
nodeargd=macrospec.ParsedMacroArgs(argspec='{{{{', argnlist=[
LatexCharsNode(parsing_state=parsing_state2,
chars='[',
pos=22,len=1),
LatexCharsNode(parsing_state=parsing_state2,
chars='L',
pos=23,len=1),
LatexCharsNode(parsing_state=parsing_state2,
chars='e',
pos=24,len=1),
LatexCharsNode(parsing_state=parsing_state2,
chars='m',
pos=25,len=1),
]),
pos=17,len=26-17),
LatexCharsNode(parsing_state=parsing_state2,
chars='ma 3]',
pos=26,len=31-26),
LatexGroupNode(parsing_state=parsing_state2,
delimiters=('{', '}'),
nodelist=[
LatexCharsNode(parsing_state=parsing_state2,
chars='Author',
pos=32,len=38-32),
],
pos=31,len=39-31),
LatexCharsNode(parsing_state=parsing_state2,p = latextext.find('$$')
self.assertEqual(
lw.get_latex_nodes(pos=p+2, stop_upon_closing_mathmode='$$', parsing_state=parsing_state),
( [ LatexCharsNode(parsing_state=parsing_state,
chars='\n ax + b = y\n',
pos=p+2,len=len('\n ax + b = y\n')), ] ,
p+2, len('\n ax + b = y\n$$') ) # len includes closing token
)
# check that first node is math mode node when parsing including the math mode start
nodes = lw.get_latex_nodes(pos=p, parsing_state=parsing_state)[0]
parsing_state_inner = nodes[0].nodelist[0].parsing_state # inner "math mode" state
self.assertEqual(
nodes[0],
LatexMathNode(parsing_state=parsing_state,
displaytype='display',
nodelist=[ LatexCharsNode(parsing_state=parsing_state_inner,
chars='\n ax + b = y\n',
pos=p+2,len=len('\n ax + b = y\n')), ],
delimiters=('$$', '$$'),
pos=p,len=len('$$\n ax + b = y\n$$'))
)
p = latextext.find(r'\[')
good_parsed_structure = lambda parsing_state, ps2, ps3: [
LatexCharsNode(parsing_state=parsing_state,
chars=' cx^2+z=-d',
pos=p+2,len=12-2),
LatexMacroNode(parsing_state=parsing_state,
macroname='quad',
pos=p+12,len=17-12),
LatexMacroNode(parsing_state=parsing_state,def iterate_over_words_in_nodelist(nodelist):
# first, split the root-level char nodes at spaces and keep the rest.
split_nodelist = []
for n in nodelist:
if n.isNodeType(latexwalker.LatexCharsNode):
# split at whitespace
chunks = re.compile(r'(\s+)').split(n.chars)
plen = 0
for chunk, sep in zip(chunks[0::2], chunks[1::2]+['']):
split_nodelist += [
(latexwalker.LatexCharsNode(parsing_state=n.parsing_state,
chars=chunk,
pos=n.pos+plen, len=len(chunk)), sep)
]
plen += len(chunk)+len(sep)
else:
split_nodelist += [(n, '')]
# now, combine them smarly into words.
cur_nodelist = []
need_protection_hint = False
for n, sep in split_nodelist:
logger.longdebug("node to consider for chunk: %r, sep=%r", n, sep)
if sep: # has separator
cur_nodelist += [n]
# flush what we've accumulated so far
yield cur_nodelist, sep, need_protection_hintif self.verbatim_arg_type == 'verbatim-environment':
# simply scan the string until we find '\end{verbatim}'. That's
# exactly how LaTeX processes it.
endverbpos = w.s.find(r'\end{verbatim}', pos)
if endverbpos == -1:
raise latexwalker.LatexWalkerParseError(
s=w.s,
pos=pos,
msg=r"Cannot find matching \end{verbatim}"
)
# do NOT include the "\end{verbatim}", latexwalker will expect to
# see it:
len_ = endverbpos-pos
argd = ParsedVerbatimArgs(
verbatim_chars_node=w.make_node(latexwalker.LatexCharsNode,
parsing_state=parsing_state,
chars=w.s[pos:pos+len_],
pos=pos,
len=len_)
)
return (argd, pos, len_)
if self.verbatim_arg_type == 'verb-macro':
# read the next nonwhitespace char. This is the delimiter of the
# argument
while w.s[pos].isspace():
pos += 1
if pos >= len(w.s):
raise latexwalker.LatexWalkerParseError(
s=w.s,
pos=pos,pylatexenc
Simple LaTeX parser providing latex-to-unicode and unicode-to-latex conversion
Package Health Score
55 / 100Popular pylatexenc functions
- pylatexenc.latex2text.EnvironmentTextSpec
- pylatexenc.latex2text.LatexNodes2Text
- pylatexenc.latex2text.MacroTextSpec
- pylatexenc.latex2text.SpecialsTextSpec
- pylatexenc.latexencode.UnicodeToLatexEncoder
- pylatexenc.latexencode.utf8tolatex
- pylatexenc.latexwalker
- pylatexenc.latexwalker.__init__.LatexToken
- pylatexenc.latexwalker.__init__.LatexWalkerEndOfStream
- pylatexenc.latexwalker.__init__.LatexWalkerParseError
- pylatexenc.latexwalker.LatexCharsNode
- pylatexenc.latexwalker.LatexGroupNode
- pylatexenc.latexwalker.LatexMacroNode
- pylatexenc.latexwalker.LatexWalker
- pylatexenc.macrospec.LatexContextDb
- pylatexenc.macrospec.MacroSpec
- pylatexenc.macrospec.MacroStandardArgsParser
- pylatexenc.macrospec.ParsedMacroArgs
- pylatexenc.macrospec.std_environment
- pylatexenc.macrospec.std_macro