From 168bb2a6ed1977e96c0a404cbb1dc6ed192c1d5c Mon Sep 17 00:00:00 2001
From: Robyn Speer <rspeer@luminoso.com>
Date: Thu, 18 Feb 2021 18:25:16 -0500
Subject: [PATCH] fix version, update instructions and changelog

---
 CHANGELOG.md | 11 +++++++++
 README.md    | 65 ++++++----------------------------------------------
 setup.py     |  8 +++++--
 3 files changed, 24 insertions(+), 60 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index dc23a9d..5460ffc 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,3 +1,14 @@
+## Version 2.4.2 (2021-02-19)
+
+- When tokenizing Japanese or Korean, MeCab's dictionaries no longer have to
+  be installed separately as system packages. They can now be found via the
+  Python packages `ipadic` and `mecab-ko-dic`.
+
+- When the tokenizer had to infer word boundaries in languages without spaces,
+  inputs that were too long (such as the letter 'l' repeated 800 times) were
+  causing overflow errors. We changed the sequence of operations so that it
+  no longer overflows, and such inputs simply get a frequency of 0.
+
 ## Version 2.4.1 (2021-02-09)
 
 - Changed a log message to not try to call a language by name, to remove
diff --git a/README.md b/README.md
index 00c453a..4f31cd7 100644
--- a/README.md
+++ b/README.md
@@ -381,67 +381,16 @@ Simplified Chinese), you will get the `zh` wordlist, for example.
 ## Additional CJK installation
 
 Chinese, Japanese, and Korean have additional external dependencies so that
-they can be tokenized correctly. Here we'll explain how to set them up,
-in increasing order of difficulty.
+they can be tokenized correctly. They can all be installed at once by requesting
+the 'cjk' feature:
 
+    pip install wordfreq[cjk]
 
-### Chinese
+Tokenizing Chinese depends on the `jieba` package, tokenizing Japanese depends
+on `mecab-python` and `ipadic`, and tokenizing Korean depends on `mecab-python`
+and `mecab-ko-dic`.
 
-To be able to look up word frequencies in Chinese, you need Jieba, a
-pure-Python Chinese tokenizer:
-
-    pip3 install jieba
-
-
-### Japanese
-
-We use MeCab, by Taku Kudo, to tokenize Japanese. To use this in wordfreq, three
-things need to be installed:
-
-  * The MeCab development library (called `libmecab-dev` on Ubuntu)
-  * The UTF-8 version of the `ipadic` Japanese dictionary
-    (called `mecab-ipadic-utf8` on Ubuntu)
-  * The `mecab-python3` Python interface
-
-To install these three things on Ubuntu, you can run:
-
-```sh
-sudo apt-get install python3-dev libmecab-dev mecab-ipadic-utf8
-pip3 install mecab-python3
-```
-
-If you choose to install `ipadic` from somewhere else or from its source code,
-be sure it's configured to use UTF-8. By default it will use EUC-JP, which will
-give you nonsense results.
-
-
-### Korean
-
-Korean also uses MeCab, with a Korean dictionary package by Yongwoon Lee and
-Yungho Yu. This dictionary is not available as an Ubuntu package.
-
-Here's a process you can use to install the Korean dictionary and the other
-MeCab dependencies:
-
-```sh
-sudo apt-get install libmecab-dev mecab-utils
-pip3 install mecab-python3
-wget https://bitbucket.org/eunjeon/mecab-ko-dic/downloads/mecab-ko-dic-2.0.1-20150920.tar.gz
-tar xvf mecab-ko-dic-2.0.1-20150920.tar.gz
-cd mecab-ko-dic-2.0.1-20150920
-./autogen.sh
-./configure
-make
-sudo make install
-```
-
-If wordfreq cannot find the Japanese or Korean data for MeCab when asked to
-tokenize those languages, it will raise an error and show you the list of
-paths it searched.
-
-Sorry that this is difficult. We tried to just package the data files we need
-with wordfreq, like we do for Chinese, but PyPI would reject the package for
-being too large.
+As of version 2.4.2, you no longer have to install dictionaries separately.
 
 
 ## License
diff --git a/setup.py b/setup.py
index f68404a..098b07b 100755
--- a/setup.py
+++ b/setup.py
@@ -33,7 +33,7 @@ dependencies = [
 
 setup(
     name="wordfreq",
-    version='2.5.0',
+    version='2.4.2',
     maintainer='Robyn Speer',
     maintainer_email='rspeer@luminoso.com',
     url='http://github.com/LuminosoInsight/wordfreq/',
@@ -55,8 +55,12 @@ setup(
     #
     # Similarly, jieba is required for Chinese word frequencies.
     extras_require={
+        # previous names for extras
         'mecab': ['mecab-python3', 'ipadic', 'mecab-ko-dic'],
-        'jieba': ['jieba >= 0.42']
+        'jieba': ['jieba >= 0.42'],
+
+        # get them all at once
+        'cjk': ['mecab-python3', 'ipadic', 'mecab-ko-dic', 'jieba >= 0.42']
     },
     tests_require=['pytest', 'mecab-python3', 'jieba >= 0.42', 'ipadic', 'mecab-ko-dic'],
 )