mkpkglists improvements

This overlaid MR changes a couple things, namely the format of the meta package archive and only updating archives when needed.

Update When Needed:

We now use the information_schema.tables AUTO_INCREMENT column to keep track of a "serial number" that can be used to tell us whether we need to update or not.

Metadata Format:

    The SQL logic in this file for package metadata now exactly
    reflects RPC's search logic, without searching for specific
    packages.

    Two command line arguments are available:

        --extended | Include License, Keywords and Groups fields

    When one of these arguments are passed, the script will create
    a packages-meta-ext-v1.json.gz, configured via packagesmetaextfile.

    Archive JSON is in the following format: line-separated package objects
    enclosed in a list:

        [
        {...},
        {...},
        {...}
        ]

    This allows users to stream the archive and process packages
    line-by-line, during the local storage process.

    Signed-off-by: Kevin Morris <kevr@0cost.org>

aurweb/scripts/mkpkglists.py

@@ -202,6 +202,17 @@ def is_decimal(column):
     return column
 
 
+def write_archive(archive: str, output: list):
+    with gzip.open(archive, "wb") as f:
+        f.write(b"[\n")
+        for i, item in enumerate(output):
+            f.write(orjson.dumps(item))
+            if i < len(output) - 1:
+                f.write(b",")
+            f.write(b"\n")
+        f.write(b"]")
+
+
 def main():
     conn = aurweb.db.Connection()
 
@@ -235,22 +246,15 @@ def main():
         # Produce packages-meta-v1.json.gz
         output = list()
         snapshot_uri = aurweb.config.get("options", "snapshot_uri")
-        with gzip.open(packagesmetafile, "wb") as f:
-            for result in cur.fetchall():
-                item = {
-                    column[0]: is_decimal(result[i])
-                    for i, column in enumerate(cur.description)
-                }
-                item["URLPath"] = snapshot_uri % item.get("Name")
-                output.append(item)
-
-            f.write(b"[\n")
-            for i, item in enumerate(output):
-                f.write(orjson.dumps(item))
-                if i < len(output) - 1:
-                    f.write(b",")
-                f.write(b"\n")
-            f.write(b"]")
+        for result in cur.fetchall():
+            item = {
+                column[0]: is_decimal(result[i])
+                for i, column in enumerate(cur.description)
+            }
+            item["URLPath"] = snapshot_uri % item.get("Name")
+            output.append(item)
+
+        write_archive(packagesmetafile, output)
 
         # Produce packages-meta-ext-v1.json.gz
         if len(sys.argv) > 1 and sys.argv[1] in EXTENDED_FIELD_HANDLERS:
@@ -262,14 +266,7 @@ def main():
                 data_ = data.get(output[i].get("ID"), default_)
                 output[i].update(data_)
 
-            with gzip.open(packagesmetaextfile, "wb") as f:
-                f.write(b"[\n")
-                for i, item in enumerate(output):
-                    f.write(orjson.dumps(item))
-                    if i < len(output) - 1:
-                        f.write(b",")
-                    f.write(b"\n")
-                f.write(b"]")
+            write_archive(packagesmetaextfile, output)
 
         # Produce packages.gz
         with gzip.open(packagesfile, "wb") as f: