From 7225ef09ba9ca10a50f449517fabdbae1f8c6f46 Mon Sep 17 00:00:00 2001
From: Arthur Baars <aibaars@github.com>
Date: Thu, 20 Apr 2023 15:00:58 +0200
Subject: [PATCH] Script for detecting out-of-sync dbscheme fragments

---
 .github/workflows/sync-files.yml  |  2 +
 config/dbscheme-fragments.json    |  6 +++
 config/sync-dbscheme-fragments.py | 76 +++++++++++++++++++++++++++++++
 3 files changed, 84 insertions(+)
 create mode 100644 config/dbscheme-fragments.json
 create mode 100755 config/sync-dbscheme-fragments.py

diff --git a/.github/workflows/sync-files.yml b/.github/workflows/sync-files.yml
index afa1e78edfa..8f4678f1788 100644
--- a/.github/workflows/sync-files.yml
+++ b/.github/workflows/sync-files.yml
@@ -17,4 +17,6 @@ jobs:
       - uses: actions/checkout@v3
       - name: Check synchronized files
         run: python config/sync-files.py
+      - name: Check dbscheme fragments
+        run: python config/sync-dbscheme-fragments.py
 
diff --git a/config/dbscheme-fragments.json b/config/dbscheme-fragments.json
new file mode 100644
index 00000000000..fdcadb53049
--- /dev/null
+++ b/config/dbscheme-fragments.json
@@ -0,0 +1,6 @@
+{
+  "files": [
+  ],
+  "fragments": [
+  ]
+}
diff --git a/config/sync-dbscheme-fragments.py b/config/sync-dbscheme-fragments.py
new file mode 100755
index 00000000000..5ada01537e9
--- /dev/null
+++ b/config/sync-dbscheme-fragments.py
@@ -0,0 +1,76 @@
+#!/usr/bin/env python3
+
+import json
+import os
+import re
+
+
+def make_groups(blocks):
+    groups = {}
+    for block in blocks:
+        groups.setdefault("".join(block["lines"]), []).append(block)
+    return list(groups.values())
+
+
+def validate_fragments(fragments):
+    ok = True
+    for header, blocks in fragments.items():
+        groups = make_groups(blocks)
+        if len(groups) > 1:
+            ok = False
+            print("Warning: dbscheme fragments with header '{}' are different for {}".format(header, ["{}:{}:{}".format(
+                group[0]["file"], group[0]["start"], group[0]["end"]) for group in groups]))
+    return ok
+
+
+def main():
+    script_dir = os.path.dirname(os.path.realpath(__file__))
+
+    with open(os.path.join(script_dir, "dbscheme-fragments.json"), "r") as f:
+        config = json.load(f)
+
+    fragment_headers = set(config["fragments"])
+    fragments = {}
+    ok = True
+    for file in config["files"]:
+        with open(os.path.join(os.path.dirname(script_dir), file), "r") as dbscheme:
+            header = None
+            line_number = 1
+            block = {"file": file, "start": line_number,
+                     "end": None, "lines": []}
+
+            def end_block():
+                block["end"] = line_number - 1
+                if len(block["lines"]) > 0:
+                    if header is None:
+                        if re.match(r'(?m)\A(\s|//.*$|/\*(\**[^\*])*\*+/)*\Z', "".join(block["lines"])):
+                            # Ignore comments at the beginning of the file
+                            pass
+                        else:
+                            ok = False
+                            print("Warning: dbscheme fragment without header: {}:{}:{}".format(
+                                block["file"], block["start"], block["end"]))
+                    else:
+                        fragments.setdefault(header, []).append(block)
+            for line in dbscheme:
+                m = re.match(r"^\/\*-.*-\*\/$", line)
+                if m:
+                    end_block()
+                    header = line.strip()
+                    if header not in fragment_headers:
+                        ok = False
+                        print("Warning: unknown header for dbscheme fragment: '{}': {}:{}".format(
+                            header, file, line_number))
+                    block = {"file": file, "start": line_number,
+                             "end": None, "lines": []}
+                block["lines"].append(line)
+                line_number += 1
+            block["lines"].append('\n')
+            line_number += 1
+            end_block()
+    if not ok or not validate_fragments(fragments):
+        exit(1)
+
+
+if __name__ == "__main__":
+    main()