From 68f0df96a9e2d1f296338307ce5e9d1c0bc085c2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gijs=20Vermari=C3=ABn?= <gijs.vermarien@gmail.com>
Date: Mon, 1 Jul 2019 13:19:39 +0200
Subject: [PATCH] Upload the filter and install script

---
 README.md            |   1 +
 install.sh           |  11 +++++
 ipynb_drop_output.py | 106 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 118 insertions(+)
 create mode 100644 README.md
 create mode 100644 install.sh
 create mode 100755 ipynb_drop_output.py

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..5a12704
--- /dev/null
+++ b/README.md
@@ -0,0 +1 @@
+A tool for scrubbing .ipynb files before each git commands applies to them
diff --git a/install.sh b/install.sh
new file mode 100644
index 0000000..f7d35ad
--- /dev/null
+++ b/install.sh
@@ -0,0 +1,11 @@
+TARGETDIR=~/.scripts/
+SCRIPT=ipynb_drop_output.py
+mkdir $TARGETDIR
+cp ./${SCRIPT} $TARGETDIR
+chmod +x $TARGETDIR$SCRIPT
+touch ~/.gitattributes
+echo "*.ipynb filter=clean_ipynb" > ~/.gitattributes
+git config --global core.attributesfile ~/.gitattributes
+git config --global filter.clean_ipynb.clean $TARGETDIR$SCRIPT
+git config --global filter.clean_ipynb.smudge cat
+echo "installed the ipynb filter"
diff --git a/ipynb_drop_output.py b/ipynb_drop_output.py
new file mode 100755
index 0000000..c296bd0
--- /dev/null
+++ b/ipynb_drop_output.py
@@ -0,0 +1,106 @@
+#!/usr/bin/env python
+
+"""
+Suppress output and prompt numbers in git version control.
+
+This script will tell git to ignore prompt numbers and cell output
+when looking at ipynb files if their metadata contains:
+
+    "git" : { "suppress_output" : true }
+
+The notebooks themselves are not changed.
+
+See also this blogpost: http://pascalbugnion.net/blog/ipython-notebooks-and-git.html.
+
+Usage instructions
+==================
+
+Make a .sh file of the following lines, and run this in order to enable the filter
+--------------
+TARGETDIR=~/.scripts/
+SCRIPT=ipynb_drop_output.py
+mkdir $TARGETDIR
+cp ./${SCRIPT} $TARGETDIR
+chmod +x $TARGETDIR$SCRIPT
+touch ~/.gitattributes
+echo "*.ipynb filter=clean_ipynb" > ~/.gitattributes
+git config --global core.attributesfile ~/.gitattributes
+git config --global filter.clean_ipynb.clean $TARGETDIR$SCRIPT
+git config --global filter.clean_ipynb.smudge cat
+echo "installed the ipynb filter"
+
+To tell git to ignore the output and prompts for a notebook,
+open the notebook's metadata (Edit > Edit Notebook Metadata). A
+panel should open containing the lines:
+--------------
+Or by hand:
+1. create ~/.scripts and paste the ipynb_drop_output.py into it
+2. Give it execution permission with chmod +x ~/.scripts/ipynb_drop_output.py
+3. Create ~/.gitattributes and paste the following text into it: "*.ipynb filter=clean_ipynb"
+4. Execute the following commands:
+    git config --global core.attributesfile ~/.gitattributes
+    git config --global filter.clean_ipynb.clean ~/.scripts/ipynb_drop_output.py
+    git config --global filter.clean_ipynb.smudge cat
+Your outputs should now be filtered!
+
+    {
+        "name" : "",
+        "signature" : "some very long hash"
+    }
+
+Add an extra line so that the metadata now looks like:
+
+    {
+        "name" : "",
+        "signature" : "don't change the hash, but add a comma at the end of the line",
+        "git" : { "suppress_outputs" : true }
+    }
+
+You may need to "touch" the notebooks for git to actually register a change, if
+your notebooks are already under version control.
+
+Notes
+=====
+
+This script is inspired by http://stackoverflow.com/a/20844506/827862, but 
+lets the user specify whether the ouptut of a notebook should be suppressed
+in the notebook's metadata, and works for IPython v3.0.
+"""
+
+import sys
+import json
+
+nb = sys.stdin.read()
+
+json_in = json.loads(nb)
+nb_metadata = json_in["metadata"]
+suppress_output = False
+#if "git" in nb_metadata:
+#    if "suppress_outputs" in nb_metadata["git"] and nb_metadata["git"]["suppress_outputs"]:
+#        suppress_output = True
+#if not suppress_output:
+#    sys.stdout.write(nb)
+#    exit() 
+
+
+ipy_version = int(json_in["nbformat"])-1 # nbformat is 1 more than actual version.
+
+def strip_output_from_cell(cell):
+    if "outputs" in cell:
+        cell["outputs"] = []
+    if "prompt_number" in cell:
+        del cell["prompt_number"]
+    if "execution_count" in cell:
+        cell["execution_count"] = None
+
+
+
+if ipy_version == 2:
+    for sheet in json_in["worksheets"]:
+        for cell in sheet["cells"]:
+            strip_output_from_cell(cell)
+else:
+    for cell in json_in["cells"]:
+        strip_output_from_cell(cell)
+
+json.dump(json_in, sys.stdout, sort_keys=True, indent=1, separators=(",",": "))