blob: render hexdump(1)-style binary blob content

Raw binary blob content tends to look like "line noise" and is rarely,
if ever, meaningful. A hexdump(1)-style rendering (specifically,
"hexdump -C"), on the other hand, showing runs of hexadecimal byte
values along with an ASCII representation of those bytes can sometimes
reveal useful information about the data.

(A subsequent patch will add the ability to cap the amount of data
rendered in order to reduce storage space requirements.)

Signed-off-by: Eric Sunshine <sunshine@sunshineco.com>
Signed-off-by: Alberto Bertogli <albertito@blitiri.com.ar>

4 files changed, 35 insertions, 2 deletions

diff --git a/git-arr b/git-arr
index d3f1151..ae509ea 100755
--- a/git-arr
+++ b/git-arr
@@ -188,6 +188,7 @@ def with_utils(f):
         'can_embed_image': utils.can_embed_image,
         'embed_image_blob': utils.embed_image_blob,
         'is_binary': utils.is_binary,
+        'hexdump': utils.hexdump,
         'abort': bottle.abort,
         'smstr': git.smstr,
     }
diff --git a/static/git-arr.css b/static/git-arr.css
index 8da2b67..a3fcadb 100644
--- a/static/git-arr.css
+++ b/static/git-arr.css
@@ -159,6 +159,18 @@ pre.blob-body {
     font-size: medium;
 }
 
+table.blob-binary pre {
+    padding: 0;
+    margin: 0;
+}
+
+table.blob-binary .offset {
+    text-align: right;
+    font-size: x-small;
+    color: darkgray;
+    border-right: 1px solid #eee;
+}
+
 /* Pygments overrides. */
 div.linenodiv {
     padding-right: 0.5em;
diff --git a/utils.py b/utils.py
index 5bea961..a7d2886 100644
--- a/utils.py
+++ b/utils.py
@@ -19,6 +19,7 @@ except ImportError:
 
 import base64
 import mimetypes
+import string
 
 def shorten(s, width = 60):
     if len(s) < 60:
@@ -106,3 +107,14 @@ def embed_image_blob(fname, image_data):
 def is_binary(s):
     # Git considers a blob binary if NUL in first ~8KB, so do the same.
     return '\0' in s[:8192]
+
+def hexdump(s):
+    graph = string.ascii_letters + string.digits + string.punctuation + ' '
+    offset = 0
+    while s:
+        t = s[:16]
+        hexvals = ['%.2x' % ord(c) for c in t]
+        text = ''.join(c if c in graph else '.' for c in t)
+        yield offset, ' '.join(hexvals[:8]), ' '.join(hexvals[8:]), text
+        offset += 16
+        s = s[16:]
diff --git a/views/blob.html b/views/blob.html
index 4526c99..74c910a 100644
--- a/views/blob.html
+++ b/views/blob.html
@@ -42,12 +42,20 @@
 % if can_embed_image(repo, fname.unicode):
 {{!embed_image_blob(fname.raw, blob.raw_content)}}
 % elif is_binary(blob.raw_content):
-<table class="nice">
+<table class="nice blob-binary">
     <tr>
-        <td>
+        <td colspan="4">
             binary &mdash; {{'{:,}'.format(len(blob.raw_content))}} bytes
         </td>
     </tr>
+%   for offset, hex1, hex2, text in hexdump(blob.raw_content):
+    <tr>
+        <td class="offset">{{offset}}</td>
+        <td><pre>{{hex1}}</pre></td>
+        <td><pre>{{hex2}}</pre></td>
+        <td><pre>{{text}}</pre></td>
+    </tr>
+%   end
 </table>
 % elif can_markdown(repo, fname.unicode):
 {{!markdown_blob(blob.utf8_content)}}