Reimplement #201

Some effect as #201, but should now pass tests

Author: Martin Durant

streamz/sources.py

@@ -50,6 +50,9 @@ class from_textfile(Source):
     start: bool (False)
         Whether to start running immediately; otherwise call stream.start()
         explicitly.
+    from_end: bool (False)
+        Whether to begin streaming from the end of the file (i.e., only emit
+        lines appended after the stream starts).
 
     Example
     -------
@@ -63,10 +66,11 @@ class from_textfile(Source):
     Stream
     """
     def __init__(self, f, poll_interval=0.100, delimiter='\n', start=False,
-                 **kwargs):
+                 from_end=False, **kwargs):
         if isinstance(f, str):
             f = open(f)
         self.file = f
+        self.from_end = from_end
         self.delimiter = delimiter
 
         self.poll_interval = poll_interval
@@ -82,6 +86,9 @@ def start(self):
     @gen.coroutine
     def do_poll(self):
         buffer = ''
+        if self.from_end:
+            # this only happens when we are ready to read
+            self.file.seek(0, 2)
         while True:
             line = self.file.read()
             if line:

streamz/tests/test_core.py

@@ -787,6 +787,25 @@ def test_from_file():
                 assert time() < start + 2  # reads within 2s
 
 
+@gen_test()
+def test_from_file_end():
+    with tmpfile() as fn:
+        with open(fn, 'wt') as f:
+            f.write('data1\n')
+            f.flush()
+
+            source = Stream.from_textfile(fn, poll_interval=0.010,
+                                          start=False, from_end=True)
+            out = source.sink_to_list()
+            source.start()
+            assert out == []
+            yield gen.sleep(0.01)
+
+            f.write('data2\n')
+            f.flush()
+            yield await_for(lambda: out == ['data2\n'], timeout=5, period=0.1)
+
+
 @gen_test()
 def test_filenames():
     with tmpfile() as fn: