iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-25 02:05:24 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Revise the build test to compare lengths of wordlists.

Browse Source 
The test currently fails on Python 3, for some strange reason.
This commit is contained in:
Rob Speer 2013-10-30 13:22:56 -04:00
parent ce07c881c5
commit 3063b3915a
3 changed files with 26 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
tests/test_build.py
View File

@ -1,9 +1,17 @@
from nose.tools import eq_
from wordfreq.build import load_all_data from wordfreq.build import load_all_data
from wordfreq.query import wordlist_info
from wordfreq.transfer import download_and_extract_raw_data from wordfreq.transfer import download_and_extract_raw_data
from wordfreq import config from wordfreq import config
import os import os
import tempfile import tempfile
import shutil import shutil
import sqlite3
def flatten_list_of_dicts(list_of_dicts):
things = [sorted(d.items()) for d in list_of_dicts]
return sorted(things)
def test_build(): def test_build():
@ -17,7 +25,10 @@ def test_build():
try: try:
db_file = os.path.join(tempdir, 'test.db') db_file = os.path.join(tempdir, 'test.db')
load_all_data(config.RAW_DATA_DIR, db_file) load_all_data(config.RAW_DATA_DIR, db_file)
conn = sqlite3.connect(db_file)
assert open(db_file).read() == open(config.DB_FILENAME).read() # Compare the information we got to the information in the default DB.
eq_(flatten_list_of_dicts(wordlist_info(conn)),
flatten_list_of_dicts(wordlist_info(None)))
finally: finally:
shutil.rmtree(tempdir) shutil.rmtree(tempdir)

4
tests/test_queries.py
View File

@ -1,7 +1,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from nose.tools import eq_, assert_almost_equal, assert_greater from nose.tools import eq_, assert_almost_equal, assert_greater
from wordfreq.query import (word_frequency, average_frequency, wordlist_size, from wordfreq.query import (word_frequency, average_frequency, wordlist_size,
get_wordlists, metanl_word_frequency) wordlist_info, metanl_word_frequency)
def test_freq_examples(): def test_freq_examples():
@ -40,7 +40,7 @@ def _check_normalized_frequencies(wordlist, lang):
def test_normalized_frequencies(): def test_normalized_frequencies():
for list_info in get_wordlists(): for list_info in wordlist_info():
wordlist = list_info['wordlist'] wordlist = list_info['wordlist']
lang = list_info['lang'] lang = list_info['lang']
yield _check_normalized_frequencies, wordlist, lang yield _check_normalized_frequencies, wordlist, lang

14
wordfreq/query.py
View File

@ -101,8 +101,18 @@ def iter_wordlist(wordlist='multi', lang=None):
return results return results
def get_wordlists(): def wordlist_info(connection=None):
c = CONN.cursor() """
Get info about all the wordlists in a database, returning their
list name, language, and number of words as 'wordlist', 'lang',
and 'count' respectively.
The database connection can be given as an argument, in order to get
information about a database other than the default configured one.
"""
if connection is None:
connection = CONN
c = connection.cursor()
results = c.execute( results = c.execute(
"SELECT wordlist, lang, count(*) from words GROUP BY wordlist, lang" "SELECT wordlist, lang, count(*) from words GROUP BY wordlist, lang"
) )