X-Git-Url: https://wannabe.guru.org/gitweb/?a=blobdiff_plain;f=directory_filter.py;h=8d03ff603d425bddc24267061a902f67ac7bb3b1;hb=36fea7f15ed17150691b5b3ead75450e575229ef;hp=d275cf24d4e23a6be64fe4073ca4b3860c83ea3c;hpb=11eeb8574b7b4620ac6fd440cb251f8aa2458f5b;p=python_utils.git

diff --git a/directory_filter.py b/directory_filter.py
index d275cf2..8d03ff6 100644
--- a/directory_filter.py
+++ b/directory_filter.py
@@ -1,19 +1,40 @@
 #!/usr/bin/env python3
 
 import hashlib
+import logging
 import os
 from typing import Any, Optional
 
+logger = logging.getLogger(__name__)
+
 
 class DirectoryFileFilter(object):
-    """A predicate that will return False if when a proposed file's
-    content to-be-written is identical to the contents of the file;
-    skip the write.
+    """A predicate that will return False if / when a proposed file's
+    content to-be-written is identical to the contents of the file on
+    disk allowing calling code to safely skip the write.
+
+    >>> testfile = '/tmp/directory_filter_text_f39e5b58-c260-40da-9448-ad1c3b2a69c2.txt'
+    >>> contents = b'This is a test'
+    >>> with open(testfile, 'wb') as wf:
+    ...     wf.write(contents)
+    14
+
+    >>> d = DirectoryFileFilter('/tmp')
+
+    >>> d.apply(contents, testfile)     # False if testfile already contains contents
+    False
+
+    >>> d.apply(b'That was a test', testfile)    # True otherwise
+    True
+
+    >>> os.remove(testfile)
+
     """
 
     def __init__(self, directory: str):
-        import file_utils
         super().__init__()
+        import file_utils
+
         if not file_utils.does_directory_exist(directory):
             raise ValueError(directory)
         self.directory = directory
@@ -30,20 +51,26 @@ class DirectoryFileFilter(object):
 
     def _update_file(self, filename: str, mtime: Optional[float] = None):
         import file_utils
+
         assert file_utils.does_file_exist(filename)
         if mtime is None:
             mtime = file_utils.get_file_raw_mtime(filename)
         if self.mtime_by_filename.get(filename, 0) != mtime:
             md5 = file_utils.get_file_md5(filename)
+            logger.debug(
+                f'Computed/stored {filename}\'s MD5 at ts={mtime} ({md5})'
+            )
             self.mtime_by_filename[filename] = mtime
             self.md5_by_filename[filename] = md5
 
     def apply(self, item: Any, filename: str) -> bool:
         self._update_file(filename)
         file_md5 = self.md5_by_filename.get(filename, 0)
+        logger.debug(f'{filename}\'s checksum is {file_md5}')
         mem_hash = hashlib.md5()
         mem_hash.update(item)
         md5 = mem_hash.hexdigest()
+        logger.debug(f'Item\'s checksum is {md5}')
         return md5 != file_md5
 
 
@@ -51,15 +78,38 @@ class DirectoryAllFilesFilter(DirectoryFileFilter):
     """A predicate that will return False if a file to-be-written to a
     particular directory is identical to any other file in that same
     directory.
+
+    i.e. this is the same as the above except that its apply() method
+    will return true not only if the contents to be written are
+    identical to the contents of filename on the disk but also it
+    returns true if there exists some other file sitting in the same
+    directory which already contains those identical contents.
+
+    >>> testfile = '/tmp/directory_filter_text_f39e5b58-c260-40da-9448-ad1c3b2a69c3.txt'
+
+    >>> contents = b'This is a test'
+    >>> with open(testfile, 'wb') as wf:
+    ...     wf.write(contents)
+    14
+
+    >>> d = DirectoryAllFilesFilter('/tmp')
+
+    >>> d.apply(contents)    # False is _any_ file in /tmp contains contents
+    False
+
+    >>> d.apply(b'That was a test')    # True otherwise
+    True
+
+    >>> os.remove(testfile)
     """
 
     def __init__(self, directory: str):
         self.all_md5s = set()
         super().__init__(directory)
-        print(self.all_md5s)
 
     def _update_file(self, filename: str, mtime: Optional[float] = None):
         import file_utils
+
         assert file_utils.does_file_exist(filename)
         if mtime is None:
             mtime = file_utils.get_file_raw_mtime(filename)
@@ -75,3 +125,9 @@ class DirectoryAllFilesFilter(DirectoryFileFilter):
         mem_hash.update(item)
         md5 = mem_hash.hexdigest()
         return md5 not in self.all_md5s
+
+
+if __name__ == '__main__':
+    import doctest
+
+    doctest.testmod()