def itertokens(self):
"""read tex tokens, including imported files"""
dirname = os.path.dirname(self.filename)
tex = TeX(file=self.filename)
tokens = tex.itertokens()
try:
while True:
token = next(tokens)
if token.data == 'input':
tokens = self.add_input(dirname, tokens)
elif token.data == 'import':
# TODO handle \subimport, and also \import* and \subimport*
print("WARNING: we don't handle \\import yet")
yield token
elif token.data == 'include':
# TODO be aware of \includeonly
tokens = self.add_input(dirname, tokens)
elif token.data == 'newcommand':
try:
name = read_macro_name(tokens)
args_or_def = read_balanced_brackets(tokens)
if args_or_def[0] == '[': # n_args
n_args = format_n_args(args_or_def)
definition = read_balanced_brackets(tokens)
else:
n_args = 0
definition = args_or_def
self.macro_lut[name] = MacroDef(
n_args, definition[1:-1])
except:
yield token
else:
for t in maybe_expand_macro(token, tokens, self.macro_lut):
yield t
except StopIteration:
pass
import sys, re
from plasTeX.TeX import TeX
from utils import pre_tokenize, post_tokenize, BASIC_SKELETON
if __name__ == '__main__':
if len(sys.argv) != 3:
print >> sys.stderr, 'Usage: python %s <tabulars> <tokenized-tabulars>' % sys.argv[
0]
sys.exit(1)
with open(sys.argv[1]) as fin:
with open(sys.argv[2], 'w') as fout:
idx = 0
for line in fin:
_, tabular = line.split('\t', 1)
idx += 1
#if idx != 11:
# continue
tex = TeX()
tex.input(BASIC_SKELETON % (pre_tokenize(tabular)))
#print (pre_tokenize(tabular))
tokens = [token for token in tex.itertokens()]
tokens_out = []
#jprint (':'.join(tokens))
tokens_out = post_tokenize(tokens)
#print (':'.join(tokens_out))
fout.write(' '.join(tokens_out)[385:-86] + '\n')