Initial commit

src/masked.py

@@ -0,0 +1,47 @@
+#!/usr/bin/env python
+"""
+Masked wordcloud
+================
+
+Using a mask you can generate wordclouds in arbitrary shapes.
+"""
+
+import os
+from os import path
+
+import matplotlib.pyplot as plt
+import numpy as np
+from PIL import Image
+from wordcloud import STOPWORDS, ImageColorGenerator, WordCloud
+
+# get data directory (using getcwd() is needed to support running example in generated IPython notebook)
+d = path.dirname(__file__) if "__file__" in locals() else os.getcwd()
+
+# Read the whole text.
+text = open(path.join(d, "work.txt")).read()
+
+# read the mask image
+# image from: https://all-free-download.com/free-vector/download/farm-cow-icon-colored-cartoon-sketch_6843157.html
+image_mask = np.array(Image.open(path.join(d, "cow-color.png")))
+image_colors = ImageColorGenerator(image_mask)
+
+stopwords = set(STOPWORDS)
+stopwords.add("said")
+
+wc = WordCloud(
+    background_color="white",
+    max_words=750,
+    mask=image_mask,
+    stopwords=stopwords,
+    contour_width=3,
+    color_func=image_colors,
+    height=1080,
+    width=1920,
+    min_word_length=3,
+)
+
+# generate word cloud
+wc.generate(text)
+
+# store to file
+wc.to_file(path.join(d, "../cow-wordcloud.png"))

src/replacements.sed

@@ -0,0 +1,34 @@
+# Remove some HTML and markdown syntax stuff
+s/<code>//
+s/<file>//
+s_</code>__
+s_</file>__
+s/^```//
+s/^```console//
+/&&/d
+/|/d
+/-/d
+/{/d
+/^\*/d
+/^\#$/d
+/^\$$/d
+/log/d
+
+# tease out some convoluted concepts
+s/^python$/Python/
+s/\[root/root/
+s/^Gluster$/GlusterFS/
+s_HTTP/1.1"_HTTP/1.1_
+s/[Ee]rror:/error/
+
+# Anything with a comma or semi-colon at the end of the line
+s/[,:]$//
+s/\.$//
+s/\[Ansible/Ansible/
+s/^Ansible\?/Ansible/
+s/^Ansible\]\]/Ansible/
+s/^ansible$/Ansible/
+s/answer/Answer/
+
+# delete blank lines last
+/^$/d