iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-23 17:31:41 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

When strings are inconsistent between py2 and 3, don't test them on py2.

Browse Source
This commit is contained in:
Robyn Speer 2013-10-31 13:11:13 -04:00
parent 52bcb99c48
commit 101e767ad9
2 changed files with 13 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
tests/test_build.py
View File

@ -7,7 +7,9 @@ import os
import tempfile
import shutil
import sqlite3
import sys
PYTHON2 = (sys.version_info.major == 2)
def flatten_list_of_dicts(list_of_dicts):
things = [sorted(d.items()) for d in list_of_dicts]
@ -28,7 +30,16 @@ def test_build():
conn = sqlite3.connect(db_file)
# 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)))
new_info = flatten_list_of_dicts(wordlist_info(conn))
old_info = flatten_list_of_dicts(wordlist_info(None))
eq_(len(new_info), len(old_info))
for i in range(len(new_info)):
# Don't test Greek and emoji on Python 2; we can't make them
# consistent with Python 3.
if PYTHON2 and ((u'lang', u'el') in new_info[i]):
continue
if PYTHON2 and ((u'wordlist', u'twitter') in new_info[i]):
continue
eq_(new_info[i], old_info[i])
finally:
shutil.rmtree(tempdir)

4
wordfreq/build.py
View File

@ -37,10 +37,6 @@ def read_multilingual_csv(filename):
for wordlang in raw_freqs:
word, lang = wordlang.rsplit('|', 1)
word = standardize_word(word)
# The CSV reader has standardized everything to uppercase.
# Fix that for the language codes, which should be lowercase.
lang = lang.lower()
unscaled[lang][word] = raw_freqs[wordlang]
scaled = {}