🏣 Clean up for arxiv

book/ebook_src/manipulating_files/change_ext_file.py

@@ -0,0 +1,30 @@
+#!/usr/bin/env python
+
+
+__author__ = "bt3"
+
+
+import os
+import sys
+import shutil
+
+def change_file_ext():
+    """ read a file and an extension from the command line and produces a copy with its extension changed"""
+    if len(sys.argv) < 2:
+        print("Usage: change_ext.py filename.old_ext 'new_ext'")
+        sys.exit()
+
+    name = os.path.splitext(sys.argv[1])[0] + "." + sys.argv[2]
+    print (name)
+
+    try:
+        shutil.copyfile(sys.argv[1], name)
+    except OSError as err:
+        print (err)
+
+
+
+if __name__ == '__main__':
+    change_file_ext()
+
+

book/ebook_src/manipulating_files/count_unique_words_files.py

@@ -0,0 +1,28 @@
+#!/usr/bin/python
+
+__author__ = "bt3"
+
+
+import collections
+import string
+import sys
+
+def count_unique_word_file():
+    if len(sys.argv) < 2:
+        print "Usage: python count_unique_word.py NAMEFILE"
+
+    words = collections.defaultdict(int)
+    strip = string.whitespace + string.punctuation + string.digits + "\"'"
+    for filename in sys.argv[1:]:
+        with open(filename) as file:
+            for line in file:
+                for word in line.lower().split():
+                    word = word.strip(strip)
+                    if len(word) > 2:
+                        words[word] = +1
+    for word in sorted(words):
+        print("'{0}' occurs {1} times.".format(word, words[word]))
+
+
+if __name__ == '__main__':
+    count_unique_word_file()

book/ebook_src/manipulating_files/count_unique_words_frequency.py

@@ -0,0 +1,15 @@
+#!/usr/bin/python
+
+__author__ = "bt3"
+
+
+import collections
+import sys
+
+def count_unique_word_freq():
+        return collections.Counter(\
+            sys.stdin.read().lower().split()).most_common(n)
+
+
+if __name__ == '__main__':
+    count_unique_word_freq()

book/ebook_src/manipulating_files/grep_word_from_files.py

@@ -0,0 +1,27 @@
+#!/usr/bin/env python
+
+
+__author__ = "bt3"
+
+import sys
+
+def grep_word_from_files():
+    ''' using iterator enumerate to create a grep command '''
+    word = sys.argv[1]
+    for filename in sys.argv[2:]:
+        with open(filename) as file:
+            for lino, line in enumerate(file, start=1):
+                if word in line:
+                    print("{0}:{1}:{2:.40}".format(filename, lino, line.rstrip()))
+
+
+if __name__ == '__main__':
+    if len(sys.argv) < 2:
+        print("Usage: grep_word_from_files.py word infile1 [infile2...]")
+        sys.exit()
+    else:
+        grep_word_from_files()
+
+
+
+

book/ebook_src/manipulating_files/remove_blank_lines.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python
+
+
+__author__ = "bt3"
+
+
+
+import os
+import sys
+
+def read_data(filename):
+    lines = []
+    fh = None
+    try:
+        fh = open(filename)
+        for line in fh:
+            if line.strip():
+                lines.append(line)
+    except (IOError, OSError) as err:
+        print(err)
+    finally:
+        if fh is not None:
+            fh.close()
+	return lines
+
+
+def write_data(lines, filename):
+    fh = None
+    try:
+        fh = open(filename, "w")
+        for line in lines:
+            fh.write(line)
+    except (EnvironmentError) as err:
+        print(err)
+	finally:
+        if fh is not None:
+            fh.close()
+
+
+def remove_blank_lines():
+    """ read a list of filenames on the command line and for each one produces another file with the same content but with no blank lines """
+
+    if len(sys.argv) < 2:
+        print ("Usage: noblank.py infile1 [infile2...]")
+
+    for filename in sys.argv[1:]:
+        lines = read_data(filename)
+        if lines:
+            write_data(lines, filename)
+
+
+if __name__ == '__main__':
+    remove_blank_lines()
+