def get_interpretation_markers(text):
roman_dec = Word("ivxlcdm")
upper_dec = Word(string.ascii_uppercase)
marker_parser = LineStart() + (
Word(string.digits) | roman_dec | upper_dec) + Suppress(".")
for citation, start, end in marker_parser.scanString(text):
return citation[0]
def parsed_title(text, appendix_letter):
digit_str_parser = (Marker(appendix_letter)
+ Suppress('-')
+ grammar.a1.copy().leaveWhitespace()
+ Optional(grammar.markerless_upper)
+ Optional(grammar.paren_upper | grammar.paren_lower)
+ Optional(grammar.paren_digit))
part_roman_parser = Marker("part") + grammar.aI
parser = LineStart() + (digit_str_parser | part_roman_parser)
for match, _, _ in parser.scanString(text):
return match
def parsed_title(text, appendix_letter):
digit_str_parser = (Marker(appendix_letter)
+ Suppress('-')
+ grammar.a1.copy().leaveWhitespace()
+ Optional(grammar.markerless_upper)
+ Optional(grammar.paren_upper | grammar.paren_lower)
+ Optional(grammar.paren_digit))
part_roman_parser = Marker("part") + grammar.aI
parser = LineStart() + (digit_str_parser | part_roman_parser)
for match, _, _ in parser.scanString(text):
return match
def mwgtofasta(wiki, evt):
from pyparsing import Word, Literal, printables, LineStart, SkipTo, Combine, nums
raw_string = wiki.getActiveEditor().GetSelectedText()
start, end = wiki.getActiveEditor().GetSelection()
fastaheader = Combine(
Literal(">").suppress() + Word(nums).setResultsName("number") +
Literal("_").suppress())
try:
data, dataStart, dataEnd = fastaheader.scanString(raw_string).next()
except StopIteration:
number = 1
dataStart = end - start
else:
number = int(data.number) + 1
wiki.getActiveEditor().SetSelectionByCharPos(start, start + dataStart)
name = Word(printables).setResultsName("name")
seq_start = Literal("5'").suppress()
seq_stop = Literal("3'").suppress()
sequence = Combine(seq_start + SkipTo(seq_stop)).setResultsName("seq")
mwg_primer = LineStart() + name + SkipTo(LineStart()) + sequence
result = mwg_primer.scanString(raw_string)
seqlist = [data for data, dataStart, dataEnd in result]
number += len(seqlist)
fasta_string = ""
for data in seqlist:
number -= 1
s = data.seq.strip("-").replace("\n", "").replace(" ", "")
fasta_string += ">{number}_{name} ({length}-mer)\n{seq}\n\n".format(
number=number, name=data.name, length=len(s), seq=s)
wiki.getActiveEditor().ReplaceSelection(fasta_string)
wiki.getActiveEditor().SetSelectionByCharPos(start,
start + len(fasta_string))
match = re.findall(regex, text)
with open("alunos.txt", "w") as f:
for m in match:
f.write(u"{} {}\n".format(m[0], m[1]).encode("utf8"))
from pyparsing import Word, Literal, printables, LineStart, SkipTo, Combine
name = Word(printables).setResultsName("name")
seq_start = Literal("5'").suppress()
seq_stop = Literal("3'").suppress()
sequence = Combine(seq_start + SkipTo(seq_stop)).setResultsName("seq")
mwg_primer = LineStart() + name + SkipTo(LineStart()) + sequence
result = mwg_primer.scanString(raw_string)
seqlist = [data for data, dataStart, dataEnd in result]
number += len(seqlist)
fasta_string = ''
for data in seqlist:
number -= 1
s = data.seq.strip("-").replace("\n", "").replace(" ", "")
fasta_string += ">{number}_{name} ({length}-mer)\n{seq}\n\n".format(
number=number, name=data.name, length=len(s), seq=s)
fasta_string
from pyparsing import Word, Literal, printables, LineStart, SkipTo, Combine
name = Word(printables).setResultsName("name")
seq_start = Literal("5'").suppress()
seq_stop = Literal("3'").suppress()
sequence = Combine(seq_start + SkipTo(seq_stop)).setResultsName("seq")
mwg_primer = LineStart() + name + SkipTo(LineStart()) + sequence
result = mwg_primer.scanString(raw_string)
seqlist = [data for data,dataStart,dataEnd in result]
number+=len(seqlist)
fasta_string = ''
for data in seqlist:
number-=1
s=data.seq.strip("-").replace("\n","").replace(" ","")
fasta_string+=">{number}_{name} ({length}-mer)\n{seq}\n\n".format(number=number,name=data.name,length=len(s),seq=s)
fasta_string
