From 9916ee5c419ebcddcb348c3919f7ebc2b6f51c06 Mon Sep 17 00:00:00 2001
From: Dimitri Merejkowsky <dimitri.merejkowsky@tanker.io>
Date: Tue, 29 Jan 2019 16:56:42 +0100
Subject: [PATCH] Replace copy by a symlink

---
 sources/06-top-words.py | 74 +----------------------------------------
 1 file changed, 1 insertion(+), 73 deletions(-)
 mode change 100644 => 120000 sources/06-top-words.py

diff --git a/sources/06-top-words.py b/sources/06-top-words.py
deleted file mode 100644
index 7bdaa8e..0000000
--- a/sources/06-top-words.py
+++ /dev/null
@@ -1,73 +0,0 @@
-import sys
-
-
-def clean_fragment(fragment):
-    result = ""
-    for c in fragment:
-        if c.isalpha() or c in ["-", "'"]:
-            result += c
-
-    return result
-
-
-def split_words(text):
-    fragments = split_fragments(text)
-    res = list()
-    for fragment in fragments:
-        fragment = fragment.lower()
-        fragment = clean_fragment(fragment)
-        if fragment:
-            res.append(fragment)
-    return res
-
-
-def split_fragments(text):
-    res = list()
-    for fragment in text.split():
-        if "’" in fragment:
-            before = fragment.split("’")[0]
-            after = fragment.split("’")[1]
-            res.append(before)
-            res.append(after)
-        else:
-            res.append(fragment)
-    return res
-
-
-def get_frequencies(words):
-    res = dict()
-    for word in words:
-        if word in res:
-            res[word] += 1
-        else:
-            res[word] = 1
-    return res
-
-
-def get_scores(frequencies):
-    res = list()
-    for word, count in frequencies.items():
-        res.append((count, word))
-    res.sort(reverse=True)
-    return res
-
-
-def print_scores(scores):
-    for count, word in scores:
-        print(count, word)
-
-
-def main():
-    if len(sys.argv) < 2:
-        sys.exit("not enough arguments")
-    filename = sys.argv[1]
-    file = open(filename)
-    contents = file.read()
-    words = split_words(contents)
-    frequencies = get_frequencies(words)
-    scores = get_scores(frequencies)
-    top_words = scores[:20]
-    print_scores(top_words)
-
-
-main()
diff --git a/sources/06-top-words.py b/sources/06-top-words.py
new file mode 120000
index 0000000..9137809
--- /dev/null
+++ b/sources/06-top-words.py
@@ -0,0 +1 @@
+topwords/6.py
\ No newline at end of file