Massive renaming!

20-plugins/README.md

@@ -0,0 +1,29 @@
+Style #19
+==============================
+
+Constraints:
+
+- The problem is decomposed using some form of abstraction
+  (procedures, functions, objects, etc.)
+
+- All or some of those abstractions are physically encapsulated into
+  their own, usually pre-compiled, packages. Main program and each of
+  the packages are compiled independently. These packages are loaded
+  dynamically by the main program, usually in the beginning (but not
+  necessarily).
+
+- Main program uses functions/objects from the dynamically-loaded
+  packages, without knowing which exact implementations will be
+  used. New implementations can be used without having to adapt or
+  recompile the main program.
+
+- External specification of which packages to load. This can be done
+  by a configuration file, path conventions, user input or other
+  mechanisms for external specification of code to be linked at run
+  time.
+
+Possible names:
+
+- No commitment
+- Plugins
+- Dependency injection

20-plugins/config.ini

@@ -0,0 +1,5 @@
+[Plugins]
+;; Options: plugins/words1.pyc, plugins/words2.pyc
+words = plugins/words1.pyc
+;; Options: plugins/frequencies1.pyc, plugins/frequencies2.pyc
+frequencies = plugins/frequencies1.pyc

20-plugins/plugins-src/compile.sh

@@ -0,0 +1,2 @@
+python -m compileall .
+cp *.pyc ../plugins

20-plugins/plugins-src/frequencies1.py

@@ -0,0 +1,11 @@
+import operator
+
+def top25(word_list):
+    word_freqs = {}
+    for w in word_list:
+        if w in word_freqs:
+            word_freqs[w] += 1
+        else:
+            word_freqs[w] = 1
+    return sorted(word_freqs.items(), key=operator.itemgetter(1), reverse=True)[:25]
+

20-plugins/plugins-src/frequencies2.py

@@ -0,0 +1,6 @@
+import operator, collections
+
+def top25(word_list):
+    counts = collections.Counter(w for w in word_list)
+    return counts.most_common(25)
+

20-plugins/plugins-src/words1.py

@@ -0,0 +1,14 @@
+import sys, re, string
+
+def extract_words(path_to_file):
+    with open(path_to_file) as f:
+        str_data = f.read()
+    pattern = re.compile('[\W_]+')
+    word_list = pattern.sub(' ', str_data).lower().split()
+
+    with open('../stop_words.txt') as f:
+        stop_words = f.read().split(',')
+    stop_words.extend(list(string.ascii_lowercase))
+
+    return [w for w in word_list if not w in stop_words]
+

20-plugins/plugins-src/words2.py

@@ -0,0 +1,7 @@
+import sys, re, string
+
+def extract_words(path_to_file):
+    words = re.findall('[a-z]{2,}', open(path_to_file).read().lower())
+    stopwords = set(open('../stop_words.txt').read().split(','))
+    return [w for w in words if w not in stopwords]
+

20-plugins/tf-20.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python
+import sys, configparser, importlib.machinery
+
+def load_plugins():
+    config = configparser.ConfigParser()
+    config.read("config.ini")
+    words_plugin = config.get("Plugins", "words")
+    frequencies_plugin = config.get("Plugins", "frequencies")
+    global tfwords, tffreqs
+#    tfwords = importlib.load_compiled('tfwords', words_plugin)
+#    tffreqs = importlib.load_compiled('tffreqs', frequencies_plugin)
+    tfwords = importlib.machinery.SourcelessFileLoader('tfwords', words_plugin).load_module()
+    tffreqs = importlib.machinery.SourcelessFileLoader('tffreqs', frequencies_plugin).load_module()
+
+load_plugins()
+word_freqs = tffreqs.top25(tfwords.extract_words(sys.argv[1]))
+
+for (w, c) in word_freqs:
+    print(w, ' - ', c)
+