ghtdak · August 29, 2015 14:06 · Sep 17, 2014 · Sep 17, 2014 · Sep 17, 2014 · Sep 17, 2014
diff --git a/about.txt b/about.txt
@@ -1,7 +0,0 @@
-
-Some info from: http://stackoverflow.com/a/19761645/4022960 though there's a bug where he uses '' instead of None.
-
-I found using the Python script too slow as a filter.  The script is invoked multiple times by git tools like tig, 
-git diff, etc.
-
-Launching a tiny python daemon and using Netcat to twist the ends together works well.

diff --git a/about.txt b/about.txt
@@ -0,0 +1,7 @@
+
+Some info from: http://stackoverflow.com/a/19761645/4022960 though there's a bug where he uses '' instead of None.
+
+I found using the Python script too slow as a filter.  The script is invoked multiple times by git tools like tig, 
+git diff, etc.
+
+Launching a tiny python daemon and using Netcat to twist the ends together works well.
diff --git a/attributes b/attributes
@@ -0,0 +1,3 @@
+# This goes in .git/info
+
+*.ipynb    filter=dropoutput_ipynb
diff --git a/initalize.sh b/initalize.sh
@@ -0,0 +1,12 @@
+#!/bin/bash
+
+# Tell the repository to use the strip filter
+
+git config filter.dropoutput_ipynb.clean /home/change_this_path/bin/stripfilter.sh
+git config filter.dropoutput_ipynb.smudge cat
+
+# Your .git/config will have the following lines added to it
+#
+# filter "dropoutput_ipynb"]
+# 	clean = /home/change_this_path/bin/stripfilter.sh
+# 	smudge = cat
diff --git a/nbstripdaemon.py b/nbstripdaemon.py
@@ -1,9 +1,12 @@
 #!/usr/bin/python
 
 import socket
-import itertools as it
 from IPython.nbformat.current import reads, writes
 
+TCP_IP = '127.0.0.1'
+TCP_PORT = 5005
+BUFFER_SIZE = 1024
+
 def processIPython(strin):
     json_in = reads(strin, 'json')
 
@@ -17,29 +20,26 @@ def processIPython(strin):
     data = writes(json_in, 'json')
     return data
 
-TCP_IP = '127.0.0.1'
-TCP_PORT = 5005
-BUFFER_SIZE = 1024  # Normally 1024, but we want fast response
-
 s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
 s.bind((TCP_IP, TCP_PORT))
 s.listen(1)
 
 while True:
     try:
         conn, addr = s.accept()
-        print 'Connection address:', addr
-        ghtBuffer = []
+        #print 'Connection address:', addr
+        buffer = []
         while 1:
             data = conn.recv(BUFFER_SIZE)
             if not data: break
-            ghtBuffer.append(data)
+            buffer.append(data)
 
-        data = "".join(ghtBuffer)
+        data = "".join(buffer)
 
         data = processIPython(data)
 
         conn.send(data)  # echo
         conn.close()
     except:
-        print "weird exception"  
+        print "weird exception, handle to taste" 
+
diff --git a/stripfilter.sh b/stripfilter.sh
@@ -1,3 +1,4 @@
 #!/bin/bash
 # This is my all time favorite script
+
 nc 127.0.0.1 5005
diff --git a/Git for IPython Notebooks b/Git for IPython Notebooks
@@ -1,7 +0,0 @@
-Managing IPython Notebooks under Git is problematic as the output (derived data) is stored in the notebook (*.ipynb) file. This bloats the repository and makes it very difficult to use Git as anything but a blob storage device.
-
-Stripping output from the Notebook is straightforward but precludes the advantages of output in the notebook.
-
-Fortunately, Git has hooks which can be used to "do the right thing", most of the time.
-
-The best discussion of how to do this right is http://stackoverflow.com/a/20844506/4022960.  

diff --git a/nbstripdaemon.py b/nbstripdaemon.py
@@ -0,0 +1,45 @@
+#!/usr/bin/python
+
+import socket
+import itertools as it
+from IPython.nbformat.current import reads, writes
+
+def processIPython(strin):
+    json_in = reads(strin, 'json')
+
+    for sheet in json_in.worksheets:
+        for cell in sheet.cells:
+            if "outputs" in cell:
+                cell.outputs = []
+            if "prompt_number" in cell:
+                cell.prompt_number = None
+
+    data = writes(json_in, 'json')
+    return data
+
+TCP_IP = '127.0.0.1'
+TCP_PORT = 5005
+BUFFER_SIZE = 1024  # Normally 1024, but we want fast response
+
+s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+s.bind((TCP_IP, TCP_PORT))
+s.listen(1)
+
+while True:
+    try:
+        conn, addr = s.accept()
+        print 'Connection address:', addr
+        ghtBuffer = []
+        while 1:
+            data = conn.recv(BUFFER_SIZE)
+            if not data: break
+            ghtBuffer.append(data)
+
+        data = "".join(ghtBuffer)
+
+        data = processIPython(data)
+
+        conn.send(data)  # echo
+        conn.close()
+    except:
+        print "weird exception"  
diff --git a/stripfilter.sh b/stripfilter.sh
@@ -0,0 +1,3 @@
+#!/bin/bash
+# This is my all time favorite script
+nc 127.0.0.1 5005
diff --git a/README → Git for IPython Notebooks b/README → Git for IPython Notebooks
diff --git a/README b/README
@@ -0,0 +1,7 @@
+Managing IPython Notebooks under Git is problematic as the output (derived data) is stored in the notebook (*.ipynb) file. This bloats the repository and makes it very difficult to use Git as anything but a blob storage device.
+
+Stripping output from the Notebook is straightforward but precludes the advantages of output in the notebook.
+
+Fortunately, Git has hooks which can be used to "do the right thing", most of the time.
+
+The best discussion of how to do this right is http://stackoverflow.com/a/20844506/4022960.
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,3 @@
		# This goes in .git/info

		*.ipynb filter=dropoutput_ipynb