From c90e36020a6993166bae1013402c30d827014317 Mon Sep 17 00:00:00 2001
From: Joshua Harlow <harlowja@yahoo-inc.com>
Date: Thu, 9 Oct 2014 17:55:36 -0700
Subject: [PATCH] Add the database schema to the sqlalchemy docs

In order to show people that are reading the docs what the current
schema for the database is create a helper tool that upgrades the
schema to the newest version and then uses tabulate to create a
restructured text version of that schema which is then included in
the documentation.

Change-Id: Id215f88430971a4a083f9739fb2ec59d971dc8fa
---
 doc/source/persistence.rst | 48 ++++++++++++++++++++++
 tools/schema_generator.py  | 83 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 131 insertions(+)
 create mode 100755 tools/schema_generator.py

diff --git a/doc/source/persistence.rst b/doc/source/persistence.rst
index 18fe6bff5..0da68de15 100644
--- a/doc/source/persistence.rst
+++ b/doc/source/persistence.rst
@@ -177,6 +177,54 @@ Useful when you need a higher level of durability than offered by the previous
 solutions. When using these connection types it is possible to resume a engine
 from a peer machine (this does not apply when using sqlite).
 
+Schema
+^^^^^^
+
+*Logbooks*
+
+==========  ========  =============
+Name        Type      Primary Key
+==========  ========  =============
+created_at  DATETIME  False
+updated_at  DATETIME  False
+uuid        VARCHAR   True
+name        VARCHAR   False
+meta        TEXT      False
+==========  ========  =============
+
+*Flow details*
+
+===========  ========  =============
+Name         Type      Primary Key
+===========  ========  =============
+created_at   DATETIME  False
+updated_at   DATETIME  False
+uuid         VARCHAR   True
+name         VARCHAR   False
+meta         TEXT      False
+state        VARCHAR   False
+parent_uuid  VARCHAR   False
+===========  ========  =============
+
+*Atom details*
+
+===========  ========  =============
+Name         Type      Primary Key
+===========  ========  =============
+created_at   DATETIME  False
+updated_at   DATETIME  False
+uuid         VARCHAR   True
+name         VARCHAR   False
+meta         TEXT      False
+atom_type    VARCHAR   False
+state        VARCHAR   False
+intention    VARCHAR   False
+results      TEXT      False
+failure      TEXT      False
+version      TEXT      False
+parent_uuid  VARCHAR   False
+===========  ========  =============
+
 .. _sqlalchemy: http://www.sqlalchemy.org/docs/
 .. _ACID: https://en.wikipedia.org/wiki/ACID
 
diff --git a/tools/schema_generator.py b/tools/schema_generator.py
new file mode 100755
index 000000000..3685a0a13
--- /dev/null
+++ b/tools/schema_generator.py
@@ -0,0 +1,83 @@
+#!/usr/bin/env python
+
+#    Copyright (C) 2014 Yahoo! Inc. All Rights Reserved.
+#
+#    Licensed under the Apache License, Version 2.0 (the "License"); you may
+#    not use this file except in compliance with the License. You may obtain
+#    a copy of the License at
+#
+#         http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
+#    WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
+#    License for the specific language governing permissions and limitations
+#    under the License.
+
+import contextlib
+import re
+
+import six
+import tabulate
+
+from taskflow.persistence.backends import impl_sqlalchemy
+
+NAME_MAPPING = {
+    'flowdetails': 'Flow details',
+    'atomdetails': 'Atom details',
+    'logbooks': 'Logbooks',
+}
+CONN_CONF = {
+    # This uses an in-memory database (aka nothing is written)
+    "connection": "sqlite://",
+}
+TABLE_QUERY = "SELECT name, sql FROM sqlite_master WHERE type='table'"
+SCHEMA_QUERY = "pragma table_info(%s)"
+
+
+def to_bool_string(val):
+    if isinstance(val, (int, bool)):
+        return six.text_type(bool(val))
+    if not isinstance(val, six.string_types):
+        val = six.text_type(val)
+    if val.lower() in ('0', 'false'):
+        return 'False'
+    if val.lower() in ('1', 'true'):
+        return 'True'
+    raise ValueError("Unknown boolean input '%s'" % (val))
+
+
+def main():
+    backend = impl_sqlalchemy.SQLAlchemyBackend(CONN_CONF)
+    with contextlib.closing(backend) as backend:
+        # Make the schema exist...
+        with contextlib.closing(backend.get_connection()) as conn:
+            conn.upgrade()
+        # Now make a prettier version of that schema...
+        tables = backend.engine.execute(TABLE_QUERY)
+        table_names = [r[0] for r in tables]
+        for i, table_name in enumerate(table_names):
+            pretty_name = NAME_MAPPING.get(table_name, table_name)
+            print("*" + pretty_name + "*")
+            # http://www.sqlite.org/faq.html#q24
+            table_name = table_name.replace("\"", "\"\"")
+            rows = []
+            for r in backend.engine.execute(SCHEMA_QUERY % table_name):
+                # Cut out the numbers from things like VARCHAR(12) since
+                # this is not very useful to show users who just want to
+                # see the basic schema...
+                row_type = re.sub(r"\(.*?\)", "", r['type']).strip()
+                if not row_type:
+                    raise ValueError("Row %s of table '%s' was empty after"
+                                     " cleaning" % (r['cid'], table_name))
+                rows.append([r['name'], row_type, to_bool_string(r['pk'])])
+            contents = tabulate.tabulate(
+                rows, headers=['Name', 'Type', 'Primary Key'],
+                tablefmt="rst")
+            print("\n%s" % contents.strip())
+            if i + 1 != len(table_names):
+                print("")
+
+
+if __name__ == '__main__':
+    main()