From d408eba679619b4b4cc0e75f383098172c7ce75e Mon Sep 17 00:00:00 2001
From: Alexandre Dulaunoy <a@foo.be>
Date: Tue, 28 Dec 2021 10:45:23 +0100
Subject: [PATCH] chg: [hashlookup] if a file cannot be read (e.g. Permission
 denied) for hashing

Those are skipped, accounted in the nonanalysed files.
---
 bin/hashlookup-analyser.py | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/bin/hashlookup-analyser.py b/bin/hashlookup-analyser.py
index d8da250..1397460 100644
--- a/bin/hashlookup-analyser.py
+++ b/bin/hashlookup-analyser.py
@@ -167,18 +167,24 @@ def lookup(value=None):
         continue
 
     sha1 = hashlib.sha1()
-    with open(fn, 'rb') as f:
-        try:
-            size = os.fstat(f.fileno()).st_size
-        except:
-            size = 0
-            pass
-        while True:
-            data = f.read(BUF_SIZE)
-            if not data:
-                break
-            sha1.update(data)
-    h = sha1.hexdigest().upper()
+    try:
+        with open(fn, 'rb') as f:
+            try:
+                size = os.fstat(f.fileno()).st_size
+            except:
+                size = 0
+                pass
+            while True:
+                data = f.read(BUF_SIZE)
+                if not data:
+                    break
+                sha1.update(data)
+        h = sha1.hexdigest().upper()
+    except Exception as e:
+        sys.stderr.write(f'Unable to read {e} file {fn}\n')
+        notanalysed_files.append(f'{fn},{e}')
+        stats['excluded'] += 1
+        pass
 
     knowncachefile = f'{CACHE_DIR}/known/{h}'
     cachefile = f'{CACHE_DIR}/unknown/{h}'