Ignore auto generated python3- maintainer scripts

1 files changed, 60 insertions, 0 deletions

diff --git a/multiarchimport.py b/multiarchimport.py
index 84eab35..7d43938 100755
--- a/multiarchimport.py
+++ b/multiarchimport.py
@@ -6,6 +6,7 @@ import hashlib
 import logging
 import multiprocessing
 import queue
+import re
 import sqlite3
 from urllib.request import urlopen
 
@@ -16,6 +17,61 @@ from dedup.debpkg import DebExtractor
 from dedup.hashing import hash_file
 from dedup.utils import fetchiter, iterate_packages
 
+PYTHON_MAINT_CONTENT = (
+    b"""#!/bin/sh
+set -e
+
+# Automatically added by dh_python3
+if command -v py3compile >/dev/null 2>&1; then
+	py3compile
+fi
+if command -v pypy3compile >/dev/null 2>&1; then
+	pypy3compile || true
+fi
+
+# End automatically added section
+""",
+    b"""#!/bin/sh
+set -e
+
+# Automatically added by dh_python3
+if command -v py3clean >/dev/null 2>&1; then
+	py3clean
+else
+	dpkg| sed -En -e '/^(.*)\\/(.+)\\.py$/s,,rm "\\1/__pycache__/\\2".*,e'
+	find /usr/lib/python3/dist-packages/ -type d -name __pycache__ -empty -print0 | xargs --null --no-run-if-empty rmdir
+fi
+
+# End automatically added section
+""",
+    b"""#!/bin/sh
+set -e
+
+# Automatically added by dh_python3
+if which py3compile >/dev/null 2>&1; then
+	py3compile
+fi
+if which pypy3compile >/dev/null 2>&1; then
+	pypy3compile || true
+fi
+
+# End automatically added section
+""",
+    b"""#!/bin/sh
+set -e
+
+# Automatically added by dh_python3
+if which py3clean >/dev/null 2>&1; then
+	py3clean
+else
+	dpkg| perl -ne 's,/([^/]*)\\.py$,/__pycache__/\\1.*, or next; unlink $_ or die $! foreach glob($_)'
+	find /usr/lib/python3/dist-packages/ -type d -name __pycache__ -empty -print0 | xargs --null --no-run-if-empty rmdir
+fi
+
+# End automatically added section
+"""
+    )
+
 def release_architectures(mirror):
     with closing(urlopen("%s/dists/testing/Release" % mirror)) as f:
         return set(deb822.Release(f)["Architectures"].split())
@@ -88,6 +144,10 @@ class MultiarchExtractor(DebExtractor):
 
     def handle_control_member(self, name, content):
         if name in ("preinst", "postinst", "prerm", "postrm"):
+            if b"dh_python3" in content:
+                generic_content = re.sub(b" -(p|L) python3-[a-z0-9+.-]+ ", b"", content)
+                if generic_content in PYTHON_MAINT_CONTENT:
+                    return
             self.result["hasscripts"] = True
 
     def handle_control_end(self):