diff --git a/.gitignore b/.gitignore
--- a/.gitignore
+++ b/.gitignore
@@ -11,3 +11,4 @@
 dist/
 version.txt
 .mypy_cache/
+venv
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,4 +1,11 @@
-# Add here external Python modules dependencies, one per line. Module names
-# should match https://pypi.python.org/pypi names. For the full spec or
-# dependency lines, see https://pip.readthedocs.org/en/1.1/requirements.html
-
+attrs==20.3.0
+attrs-strict==0.2.0
+Deprecated==1.2.10
+hypothesis==5.49.0
+iso8601==0.1.13
+psycopg2==2.8.6
+python-dateutil==2.8.1
+six==1.15.0
+sortedcontainers==2.3.0
+typing-extensions==3.7.4.3
+wrapt==1.12.1
diff --git a/swh/clearlydefined/mapping_utils.py b/swh/clearlydefined/mapping_utils.py
new file mode 100644
--- /dev/null
+++ b/swh/clearlydefined/mapping_utils.py
@@ -0,0 +1,20 @@
+# Copyright (C) 2017-2020  The Software Heritage developers
+# See the AUTHORS file at the top-level directory of this distribution
+# License: GNU Affero General Public License version 3, or any later version
+# See top-level LICENSE file for more information
+
+import psycopg2
+import swh.model.hashutil
+
+def map_sha1_with_swhid(sha1, dsn):
+    if not sha1:
+        return None
+    read_connection = psycopg2.connect(dsn)
+    cur = read_connection.cursor()
+    sha1 = swh.model.hashutil.hash_to_hex(sha1)
+    sha1 = "\\x{sha1}".format(sha1=sha1)
+    cur.execute("SELECT sha1_git from content WHERE sha1=%s;",(sha1))
+    sha1_git = cur.fetchall()
+    sha1_git = swh.model.hashutil.hash_to_hex(sha1_git[0][0])
+    swh_id = "swh:1:cnt:{sha1_git}".format(sha1_git)
+    return swh_id