def dotest(terms, expected, which):
files = filelist(rootdir)
terms = words(terms)
# print(terms)
if which == 0:
linear_docs = linear_search(files, terms)
# print(filenames(linear_docs))
names = filenames(linear_docs)
names.sort()
expected.sort()
#assert filenames(linear_docs) == expected
assert names == expected, "found "+str(names)+" != expected "+str(expected)
elif which == 1:
index = create_index(files)
index_docs = index_search(files, index, terms)
# print(filenames(index_docs))
names = filenames(index_docs)
names.sort()
expected.sort()
#assert filenames(index_docs) == expected
assert names == expected, "found "+str(names)+" != expected "+str(expected)
else:
index = myhtable_create_index(files)
index_docs = myhtable_index_search(files, index, terms)
# print(filenames(index_docs))
names = filenames(index_docs)
names.sort()
expected.sort()
#assert filenames(index_docs) == expected
assert names == expected, "found "+str(names)+" != expected "+str(expected)
def dotest(terms, expected, which):
files = filelist(rootdir)
terms = words(terms)
# print(terms)
if which == 0:
linear_docs = linear_search(files, terms)
# print(filenames(linear_docs))
names = filenames(linear_docs)
names.sort()
expected.sort()
#assert filenames(linear_docs) == expected
assert names == expected, "found "+str(names)+" != expected "+str(expected)
elif which == 1:
index = create_index(files)
index_docs = index_search(files, index, terms)
# print(filenames(index_docs))
names = filenames(index_docs)
names.sort()
expected.sort()
#assert filenames(index_docs) == expected
assert names == expected, "found "+str(names)+" != expected "+str(expected)
else:
index = myhtable_create_index(files)
index_docs = myhtable_index_search(files, index, terms)
# print(filenames(index_docs))
names = filenames(index_docs)
names.sort()
expected.sort()
#assert filenames(index_docs) == expected
assert names == expected, "found "+str(names)+" != expected "+str(expected)
def test_linear_berlitz_none():
terms = "missspellinnng"
files = filelist(rootdir)
terms = words(terms)
linear_docs = linear_search(files, terms)
expected = []
assert filenames(linear_docs)==expected
def test_linear_berlitz():
terms = "hawaii travel"
files = filelist(rootdir)
terms = words(terms)
linear_docs = linear_search(files, terms)
expected = ['HistoryHawaii.txt']
assert filenames(linear_docs)==expected
def test_linear_berlitz_none():
terms = "missspellinnng"
files = filelist(rootdir)
terms = words(terms)
linear_docs = linear_search(files, terms)
expected = []
assert filenames(linear_docs) == expected
def test_linear_berlitz():
terms = "hawaii travel"
files = filelist(rootdir)
terms = words(terms)
linear_docs = linear_search(files, terms)
expected = ['HistoryHawaii.txt']
assert filenames(linear_docs) == expected
def test_myhtable_berlitz():
terms = "hawaii travel"
files = filelist(rootdir)
terms = words(terms)
index = myhtable_create_index(files)
myhtable_docs = myhtable_index_search(files, index, terms)
expected = ['HistoryHawaii.txt']
assert filenames(myhtable_docs) == expected
def test_myhtable_berlitz_none():
terms = "missspellinnng"
files = filelist(rootdir)
terms = words(terms)
index = myhtable_create_index(files)
myhtable_docs = myhtable_index_search(files, index, terms)
expected = []
assert filenames(myhtable_docs) == expected
def test_myhtable_berlitz_none():
terms = "missspellinnng"
files = filelist(rootdir)
terms = words(terms)
index = myhtable_create_index(files)
myhtable_docs = myhtable_index_search(files, index, terms)
expected = []
assert filenames(myhtable_docs) == expected
def test_myhtable_berlitz():
terms = "hawaii travel"
files = filelist(rootdir)
terms = words(terms)
index = myhtable_create_index(files)
myhtable_docs = myhtable_index_search(files, index, terms)
expected = ['HistoryHawaii.txt']
assert filenames(myhtable_docs) == expected
from index_search import index_search, create_index
from linear_search import linear_search
from myhtable_search import myhtable_index_search, myhtable_create_index
from words import filelist, words, results
"""
Usage:
$ python search.py linear ~/data/slate
$ python search.py index ~/data/slate
$ python search.py myhtable ~/data/slate
"""
impl = sys.argv[1]
rootdir = sys.argv[2]
files = filelist(rootdir)
# Uncomment the next line to test just the first 100 files instead of all files
# files = files[:100]
N = len(files)
print N, "files"
index = None
while True:
terms = raw_input("Search terms: ")
terms = words(terms)
if impl == 'linear':
docs = linear_search(files, terms)
elif impl == 'index':
if index is None:
from index_search import index_search, create_index
from linear_search import linear_search
from myhtable_search import myhtable_index_search, myhtable_create_index
from words import filelist, words, results
"""
Usage:
$ python search.py linear ~/data/slate
$ python search.py index ~/data/slate
$ python search.py myhtable ~/data/slate
"""
impl = sys.argv[1]
rootdir = sys.argv[2]
files = filelist(rootdir)
# Uncomment the next line to test just the first 100 files instead of all files
# files = files[:100]
N = len(files)
print(N, "files")
index = None
while True:
terms = input("Search terms: ")
terms = words(terms)
if impl=='linear':
docs = linear_search(files, terms)
elif impl == 'index':
if index is None:
from index_search import index_search, create_index
from linear_search import linear_search
from myhtable_search import myhtable_index_search, myhtable_create_index
from words import filelist, words, results
"""
Usage:
$ python search.py linear ~/data/slate
$ python search.py index ~/data/slate
$ python search.py myhtable ~/data/slate
"""
impl = sys.argv[1] # EX: "linear" or "index" or "myhtable"
rootdir = sys.argv[2] # EX: "~/data/slate"
files = filelist(
rootdir
) # This is a list of (.txt) file names, under each sub dir (from "1" to "55") of the "slate" dir
# Uncomment the next line to test just the first 100 files instead of all files
# files = files[:100]
N = len(files) # N will be 4530
print(N, "files")
index = None
while True:
terms = input("Search terms: ") # EX: "Ronald Reagan"
terms = words(terms) # EX: ['reagan', 'ronald']
if impl == 'linear':
# print("YES")
