Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Major dictionary fixes #165

Merged
merged 4 commits into from
Dec 28, 2023
Merged

Major dictionary fixes #165

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
376f04a
update dictionary builds to include testing against a clean dictionary
barrust Dec 28, 2023
a96d087
fix tests
barrust Dec 28, 2023
9654442
fixed tests
barrust Dec 28, 2023
3f1b2d3
force *_include files to be lower case
barrust Dec 28, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,9 @@
# pyspellchecker

## Version 0.7.4

* Leveraged the dictionary files from [levidromelist](https://www.levidromelist.com/levidrome-list/dictionary) to attempt to clean up the `en`, `es`, `fr`, `pt`, `'de`, and `nl`dictionaries; Attempts to resolve issues #164, #155, #150, #140, #115, and #107; see [issue #126](https://github.com/barrust/pyspellchecker/issues/126)

## Version 0.7.3

* Remove relative imports in favor of absolute imports
Expand Down
189 changes: 154 additions & 35 deletions scripts/build_dictionary.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,13 +22,12 @@
required.
"""
import contextlib
import json
import gzip
import json
import os
import string
from collections import Counter


STRING_PUNCTUATION = tuple(string.punctuation)
DIGETS = tuple(string.digits)
MINIMUM_FREQUENCY = 50
Expand Down Expand Up @@ -80,10 +79,10 @@ def build_word_frequency(filepath, language, output_path):
"""
# NLTK is only needed in this portion of the project
try:
import nltk
from nltk.tag import pos_tag
from nltk.tokenize import WhitespaceTokenizer
from nltk.tokenize.toktok import ToktokTokenizer
import nltk
except ImportError as ex:
raise ImportError("To build a dictioary from scratch, NLTK is required!\n{}".format(ex.message))

Expand Down Expand Up @@ -140,7 +139,7 @@ def export_misfit_words(misfit_filepath, word_freq_filepath, word_frequency):
file.write("\n")


def clean_english(word_frequency, filepath_exclude, filepath_include):
def clean_english(word_frequency, filepath_exclude, filepath_include, filepath_dictionary):
"""Clean an English word frequency list

Args:
Expand Down Expand Up @@ -243,19 +242,38 @@ def clean_english(word_frequency, filepath_exclude, filepath_include):
if line in word_frequency:
word_frequency.pop(line)

# Use a dictionary to clean up everything else...
final_words_to_remove = []
with load_file(filepath_dictionary) as fobj:
dictionary_words = []
for line in fobj:
if line[0] in letters and line.islower():
line = line.strip()
dictionary_words.append(line)

for word in word_frequency:
if word not in dictionary_words:
final_words_to_remove.append(word)
for word in final_words_to_remove:
word_frequency.pop(word)

for word in dictionary_words:
if word not in word_frequency:
word_frequency[word] = MINIMUM_FREQUENCY

# Add known missing words back in (ugh)
with load_file(filepath_include) as fobj:
for line in fobj:
line = line.strip()
line = line.strip().lower()
if line in word_frequency:
print("{} is already found in the dictionary! Skipping!")
print("{} is already found in the dictionary! Skipping!".format(line))
else:
word_frequency[line] = MINIMUM_FREQUENCY

return word_frequency


def clean_spanish(word_frequency, filepath_exclude, filepath_include):
def clean_spanish(word_frequency, filepath_exclude, filepath_include, filepath_dictionary):
"""Clean a Spanish word frequency list

Args:
Expand Down Expand Up @@ -336,19 +354,38 @@ def clean_spanish(word_frequency, filepath_exclude, filepath_include):
if line in word_frequency:
word_frequency.pop(line)

# Use a dictionary to clean up everything else...
final_words_to_remove = []
with load_file(filepath_dictionary) as fobj:
dictionary_words = []
for line in fobj:
if line[0] in letters and line.islower():
line = line.strip()
dictionary_words.append(line)

for word in word_frequency:
if word not in dictionary_words:
final_words_to_remove.append(word)
for word in final_words_to_remove:
word_frequency.pop(word)

for word in dictionary_words:
if word not in word_frequency:
word_frequency[word] = MINIMUM_FREQUENCY

# Add known missing words back in (ugh)
with load_file(filepath_include) as fobj:
for line in fobj:
line = line.strip()
line = line.strip().lower()
if line in word_frequency:
print("{} is already found in the dictionary! Skipping!")
print("{} is already found in the dictionary! Skipping!".format(line))
else:
word_frequency[line] = MINIMUM_FREQUENCY

return word_frequency


def clean_german(word_frequency, filepath_exclude, filepath_include):
def clean_german(word_frequency, filepath_exclude, filepath_include, filepath_dictionary):
"""Clean a German word frequency list

Args:
Expand Down Expand Up @@ -393,19 +430,38 @@ def clean_german(word_frequency, filepath_exclude, filepath_include):
if line in word_frequency:
word_frequency.pop(line)

# Use a dictionary to clean up everything else...
final_words_to_remove = []
with load_file(filepath_dictionary) as fobj:
dictionary_words = []
for line in fobj:
if line[0] in letters and line.islower():
line = line.strip()
dictionary_words.append(line)

for word in word_frequency:
if word not in dictionary_words:
final_words_to_remove.append(word)
for word in final_words_to_remove:
word_frequency.pop(word)

for word in dictionary_words:
if word not in word_frequency:
word_frequency[word] = MINIMUM_FREQUENCY

# Add known missing words back in (ugh)
with load_file(filepath_include) as fobj:
for line in fobj:
line = line.strip()
line = line.strip().lower()
if line in word_frequency:
print("{} is already found in the dictionary! Skipping!")
print("{} is already found in the dictionary! Skipping!".format(line))
else:
word_frequency[line] = MINIMUM_FREQUENCY

return word_frequency


def clean_french(word_frequency, filepath_exclude, filepath_include):
def clean_french(word_frequency, filepath_exclude, filepath_include, filepath_dictionary):
"""Clean a French word frequency list

Args:
Expand Down Expand Up @@ -450,19 +506,38 @@ def clean_french(word_frequency, filepath_exclude, filepath_include):
if line in word_frequency:
word_frequency.pop(line)

# Use a dictionary to clean up everything else...
final_words_to_remove = []
with load_file(filepath_dictionary) as fobj:
dictionary_words = []
for line in fobj:
if line[0] in letters and line.islower():
line = line.strip()
dictionary_words.append(line)

for word in word_frequency:
if word not in dictionary_words:
final_words_to_remove.append(word)
for word in final_words_to_remove:
word_frequency.pop(word)

for word in dictionary_words:
if word not in word_frequency:
word_frequency[word] = MINIMUM_FREQUENCY

# Add known missing words back in (ugh)
with load_file(filepath_include) as fobj:
for line in fobj:
line = line.strip()
line = line.strip().lower()
if line in word_frequency:
print("{} is already found in the dictionary! Skipping!")
print("{} is already found in the dictionary! Skipping!".format(line))
else:
word_frequency[line] = MINIMUM_FREQUENCY

return word_frequency


def clean_portuguese(word_frequency, filepath_exclude, filepath_include):
def clean_portuguese(word_frequency, filepath_exclude, filepath_include, filepath_dictionary):
"""Clean a Portuguese word frequency list

Args:
Expand Down Expand Up @@ -507,12 +582,31 @@ def clean_portuguese(word_frequency, filepath_exclude, filepath_include):
if line in word_frequency:
word_frequency.pop(line)

# Use a dictionary to clean up everything else...
final_words_to_remove = []
with load_file(filepath_dictionary, encoding="latin-1") as fobj:
dictionary_words = []
for line in fobj:
if line[0] in letters and line.islower():
line = line.strip()
dictionary_words.append(line)

for word in word_frequency:
if word not in dictionary_words:
final_words_to_remove.append(word)
for word in final_words_to_remove:
word_frequency.pop(word)

for word in dictionary_words:
if word not in word_frequency:
word_frequency[word] = MINIMUM_FREQUENCY

# Add known missing words back in (ugh)
with load_file(filepath_include) as fobj:
for line in fobj:
line = line.strip()
line = line.strip().lower()
if line in word_frequency:
print("{} is already found in the dictionary! Skipping!")
print("{} is already found in the dictionary! Skipping!".format(line))
else:
word_frequency[line] = MINIMUM_FREQUENCY

Expand Down Expand Up @@ -586,9 +680,9 @@ def clean_russian(word_frequency, filepath_exclude, filepath_include):
# Add known missing words back in (ugh)
with load_file(filepath_include) as fobj:
for line in fobj:
line = line.strip()
line = line.strip().lower()
if line in word_frequency:
print("{} is already found in the dictionary! Skipping!")
print("{} is already found in the dictionary! Skipping!".format(line))
else:
word_frequency[line] = MINIMUM_FREQUENCY

Expand Down Expand Up @@ -643,9 +737,9 @@ def clean_arabic(word_frequency, filepath_exclude, filepath_include):
# Add known missing words back in (ugh)
with load_file(filepath_include) as fobj:
for line in fobj:
line = line.strip()
line = line.strip().lower()
if line in word_frequency:
print("{} is already found in the dictionary! Skipping!")
print("{} is already found in the dictionary! Skipping!".format(line))
else:
word_frequency[line] = MINIMUM_FREQUENCY

Expand Down Expand Up @@ -700,9 +794,9 @@ def clean_basque(word_frequency, filepath_exclude, filepath_include):
# Add known missing words back in (ugh)
with load_file(filepath_include) as fobj:
for line in fobj:
line = line.strip()
line = line.strip().lower()
if line in word_frequency:
print("{} is already found in the dictionary! Skipping!")
print("{} is already found in the dictionary! Skipping!".format(line))
else:
word_frequency[line] = MINIMUM_FREQUENCY

Expand Down Expand Up @@ -785,16 +879,16 @@ def clean_latvian(word_frequency, filepath_exclude, filepath_include):
# Add known missing words back in (ugh)
with load_file(filepath_include) as fobj:
for line in fobj:
line = line.strip()
line = line.strip().lower()
if line in word_frequency:
print("{} is already found in the dictionary! Skipping!")
print("{} is already found in the dictionary! Skipping!".format(line))
else:
word_frequency[line] = MINIMUM_FREQUENCY

return word_frequency


def clean_dutch(word_frequency, filepath_exclude, filepath_include):
def clean_dutch(word_frequency, filepath_exclude, filepath_include, filepath_dictionary):
"""Clean a Dutch word frequency list

Args:
Expand Down Expand Up @@ -897,12 +991,31 @@ def clean_dutch(word_frequency, filepath_exclude, filepath_include):
if line in word_frequency:
word_frequency.pop(line)

# Use a dictionary to clean up everything else...
final_words_to_remove = []
with load_file(filepath_dictionary) as fobj:
dictionary_words = []
for line in fobj:
if line[0] in letters and line.islower():
line = line.strip()
dictionary_words.append(line)

for word in word_frequency:
if word not in dictionary_words:
final_words_to_remove.append(word)
for word in final_words_to_remove:
word_frequency.pop(word)

for word in dictionary_words:
if word not in word_frequency:
word_frequency[word] = MINIMUM_FREQUENCY

# Add known missing words back in (ugh)
with load_file(filepath_include) as fobj:
for line in fobj:
line = line.strip()
line = line.strip().lower()
if line in word_frequency:
print("{} is already found in the dictionary! Skipping!")
print("{} is already found in the dictionary! Skipping!".format(line))
else:
word_frequency[line] = MINIMUM_FREQUENCY

Expand Down Expand Up @@ -984,15 +1097,20 @@ def _parse_args():

# clean up the dictionary
if args.language == "en":
word_frequency = clean_english(word_frequency, exclude_filepath, include_filepath)
dict_path = os.path.abspath("{}/levidromelist-dicts/american-english-large.txt".format(data_path))
word_frequency = clean_english(word_frequency, exclude_filepath, include_filepath, dict_path)
elif args.language == "es":
word_frequency = clean_spanish(word_frequency, exclude_filepath, include_filepath)
dict_path = os.path.abspath("{}/levidromelist-dicts/spanish.txt".format(data_path))
word_frequency = clean_spanish(word_frequency, exclude_filepath, include_filepath, dict_path)
elif args.language == "de":
word_frequency = clean_german(word_frequency, exclude_filepath, include_filepath)
dict_path = os.path.abspath("{}/levidromelist-dicts/new_german.txt".format(data_path))
word_frequency = clean_german(word_frequency, exclude_filepath, include_filepath, dict_path)
elif args.language == "fr":
word_frequency = clean_french(word_frequency, exclude_filepath, include_filepath)
dict_path = os.path.abspath("{}/levidromelist-dicts/french.txt".format(data_path))
word_frequency = clean_french(word_frequency, exclude_filepath, include_filepath, dict_path)
elif args.language == "pt":
word_frequency = clean_portuguese(word_frequency, exclude_filepath, include_filepath)
dict_path = os.path.abspath("{}/levidromelist-dicts/portuguese.txt".format(data_path))
word_frequency = clean_portuguese(word_frequency, exclude_filepath, include_filepath, dict_path)
elif args.language == "ru":
word_frequency = clean_russian(word_frequency, exclude_filepath, include_filepath)
elif args.language == "ar":
Expand All @@ -1002,7 +1120,8 @@ def _parse_args():
elif args.language == "lv":
word_frequency = clean_latvian(word_frequency, exclude_filepath, include_filepath)
elif args.language == "nl":
word_frequency = clean_dutch(word_frequency, exclude_filepath, include_filepath)
dict_path = os.path.abspath("{}/levidromelist-dicts/dutch.txt".format(data_path))
word_frequency = clean_dutch(word_frequency, exclude_filepath, include_filepath, dict_path)

# export word frequency for review!
word_frequency_path = os.path.join(script_path, "{}.json".format(args.language))
Expand Down
Loading