commit ced11be761b4898fa042fba45e17e68c4d5e1ccf
parent 594dcc343ea4f9e58d42befc0f5505625c5107c6
Author: amin <dev@aminmesbah.com>
Date: Sun, 31 Jan 2016 23:11:51 +0000
make find_matches() find the indices of matching symbols
FossilOrigin-Name: f898716621d34c43f49646c6008915f2cd30279d4b48e4b469f5d55353a14860
Diffstat:
2 files changed, 14 insertions(+), 3 deletions(-)
diff --git a/speller.py b/speller.py
@@ -15,7 +15,6 @@ def main():
print(single_matches, pair_matches)
-
def tokenize_sequence(sequence):
t = namedtuple('Tokens', (['single', 'pair']))
@@ -28,12 +27,13 @@ def tokenize_sequence(sequence):
def find_matches(sequence, symbols):
matches = []
+ indices = []
lower_symbols = [i.lower() for i in symbols]
lower_sequence = [i.lower() for i in sequence]
for i in lower_sequence:
matches += (x for x in lower_symbols if x == i)
- # TODO: Make this return an array of indices
+ indices += (lower_symbols.index(x) for x in lower_symbols if x == i)
return matches
diff --git a/tests.py b/tests.py
@@ -30,7 +30,18 @@ class TokensTest(unittest.TestCase):
class FileTest(unittest.TestCase):
file_name = "elements.csv"
- proper_data = ['H', 'He', 'Li', 'Be', 'B', 'C', 'N', 'O', 'F', 'Ne', 'Na', 'Mg', 'Al', 'Si', 'P', 'S', 'Cl', 'Ar', 'K', 'Ca', 'Sc', 'Ti', 'V', 'Cr', 'Mn', 'Fe', 'Co', 'Ni', 'Cu', 'Zn', 'Ga', 'Ge', 'As', 'Se', 'Br', 'Kr', 'Rb', 'Sr', 'Y', 'Zr', 'Nb', 'Mo', 'Tc', 'Ru', 'Rh', 'Pd', 'Ag', 'Cd', 'In', 'Sn', 'Sb', 'Te', 'I', 'Xe', 'Cs', 'Ba', 'La', 'Ce', 'Pr', 'Nd', 'Pm', 'Sm', 'Eu', 'Gd', 'Tb', 'Dy', 'Ho', 'Er', 'Tm', 'Yb', 'Lu', 'Hf', 'Ta', 'W', 'Re', 'Os', 'Ir', 'Pt', 'Au', 'Hg', 'Tl', 'Pb', 'Bi', 'Po', 'At', 'Rn', 'Fr', 'Ra', 'Ac', 'Th', 'Pa', 'U', 'Np', 'Pu', 'Am', 'Cm', 'Bk', 'Cf', 'Es', 'Fm', 'Md', 'No', 'Lr', 'Rf', 'Db', 'Sg', 'Bh', 'Hs', 'Mt', 'Ds', 'Rg', 'Uub', 'Uut', 'Uuq', 'Uup', 'Uuh', 'Uus', 'Uuo']
+ proper_data = ['H', 'He', 'Li', 'Be', 'B', 'C', 'N', 'O', 'F', 'Ne',
+ 'Na', 'Mg', 'Al', 'Si', 'P', 'S', 'Cl', 'Ar', 'K', 'Ca',
+ 'Sc', 'Ti', 'V', 'Cr', 'Mn', 'Fe', 'Co', 'Ni', 'Cu', 'Zn',
+ 'Ga', 'Ge', 'As', 'Se', 'Br', 'Kr', 'Rb', 'Sr', 'Y', 'Zr',
+ 'Nb', 'Mo', 'Tc', 'Ru', 'Rh', 'Pd', 'Ag', 'Cd', 'In', 'Sn',
+ 'Sb', 'Te', 'I', 'Xe', 'Cs', 'Ba', 'La', 'Ce', 'Pr', 'Nd',
+ 'Pm', 'Sm', 'Eu', 'Gd', 'Tb', 'Dy', 'Ho', 'Er', 'Tm', 'Yb',
+ 'Lu', 'Hf', 'Ta', 'W', 'Re', 'Os', 'Ir', 'Pt', 'Au', 'Hg',
+ 'Tl', 'Pb', 'Bi', 'Po', 'At', 'Rn', 'Fr', 'Ra', 'Ac', 'Th',
+ 'Pa', 'U', 'Np', 'Pu', 'Am', 'Cm', 'Bk', 'Cf', 'Es', 'Fm',
+ 'Md', 'No', 'Lr', 'Rf', 'Db', 'Sg', 'Bh', 'Hs', 'Mt', 'Ds',
+ 'Rg', 'Uub', 'Uut', 'Uuq', 'Uup', 'Uuh', 'Uus', 'Uuo']
def test_file_contains_proper_data(self):
data = speller.get_csv_data(self.file_name, 1)
