Merge pull request #2226 from merenlab/v22-to-v23-migration

V22 to v23 contigs-db migration

anvio/dbops.py

@@ -4276,7 +4276,7 @@ def list_available_hmm_sources(self):
 
 
     def remove_data_from_db(self, tables_dict):
-        """This is quite an experimental function to clean up tables in contgis databases. Use with caution.
+        """This is quite an experimental function to clean up tables in contigs databases. Use with caution.
 
            The expected tables dict should follow this structure:
 

anvio/migrations/contigs/v22_to_v23.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python
+# -*- coding: utf-8
+
+import sys
+import argparse
+
+import anvio.db as db
+import anvio.utils as utils
+import anvio.terminal as terminal
+
+from anvio.errors import ConfigError
+
+current_version, next_version = [x[1:] for x in __name__.split('_to_')]
+
+run = terminal.Run()
+progress = terminal.Progress()
+
+def migrate(db_path):
+    if db_path is None:
+        raise ConfigError("No database path is given.")
+
+    utils.is_contigs_db(db_path)
+
+    contigs_db = db.DB(db_path, None, ignore_version = True)
+    if str(contigs_db.get_version()) != current_version:
+        raise ConfigError(f"The version of the provided contigs database is {contigs_db.get_version()}, "
+                          f"not the required version, {current_version}, so this script cannot upgrade the database.")
+
+    db_altered = False
+    progress.new("Migrating")
+
+    # usually we never need to do this, but in this case it is best practice to test if
+    # we need an actual removal of the SCGs from a contigs-db since we released new SCGs
+    # in the master repository, and some people likely already updated their contigs-dbs.
+    # if they have already gone through that, we can save them the trouble.
+    scg_taxonomy_was_run = contigs_db.get_meta_value('scg_taxonomy_was_run')
+    scg_taxonomy_db_version = contigs_db.get_meta_value('scg_taxonomy_database_version')
+    if scg_taxonomy_was_run and scg_taxonomy_db_version == "GTDB: v214.1; Anvi'o: v1":
+        # does not need an update.
+        pass
+    else:
+        # needs an update
+        contigs_db._exec('''DELETE FROM scg_taxonomy''')
+        contigs_db.set_meta_value('scg_taxonomy_was_run', 0)
+        contigs_db.set_meta_value('scg_taxonomy_database_version', None)
+
+        db_altered = True
+
+    progress.update("Updating version")
+    contigs_db.remove_meta_key_value_pair('version')
+    contigs_db.set_version(next_version)
+
+    progress.update("Committing changes")
+    contigs_db.disconnect()
+
+    progress.end()
+
+    if db_altered:
+        message = (f"Your contigs database is now version {next_version}. Sadly this update removed all SCG taxonomy "
+                   f"data in this contigs-db due to a change in the set of SCGs anvi'o now uses for taxonomy estimation. "
+                   f"As a result, you will need to re-run anvi-run-scg-taxonomy command on this contigs-db :/ If you "
+                   f"would like to learn why this was necessary, please visit https://github.com/merenlab/anvio/issues/2211. "
+                   f"We thank you for your patience!")
+    else:
+        message = ("Since you have already updated your contigs-db with new SCGs, anvi'o simply bumped the version of your "
+                   "database rather than removing or editing any data :) Moving on.")
+
+    run.info_single(message, nl_after=1, nl_before=1, mc='green')
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description=f"A simple script to upgrade an anvi'o contigs database from version {current_version} to version {next_version}")
+    parser.add_argument("contigs_db", metavar="CONTIGS_DB", help=f"An anvi'o contigs database of version {current_version}")
+    args, unknown = parser.parse_known_args()
+
+    try:
+        migrate(args.contigs_db)
+    except ConfigError as e:
+        print(e)
+        sys.exit(-1)

anvio/tables/__init__.py

@@ -14,7 +14,7 @@
 __email__ = "[email protected]"
 
 
-contigs_db_version = "22"
+contigs_db_version = "23"
 profile_db_version = "40"
 genes_db_version = "6"
 pan_db_version = "17"

bin/anvi-migrate

@@ -19,7 +19,7 @@ from anvio.migrations import migration_scripts
 
 
 __description__ = "Migrates any anvi'o artifact, whether it is a database or a config file, to a newer version. Pure magic."
-__authors__ = ['meren', 'ozcan', 'ekiefl', 'ivagljiva', 'semiller10']
+__authors__ = ['meren', 'ozcan', 'ekiefl', 'ivagljiva', 'semiller10', 'mschecht']
 __requires__ = ["contigs-db", "profile-db", "pan-db", "genes-db", "genomes-storage-db", "structure-db", "modules-db", "workflow-config"]
 __provides__ = []
 
@@ -270,7 +270,7 @@ class Migrater(object):
                     shutil.move(self.artifact_path, self.artifact_path + '.broken')
 
                     raise ConfigError("Anvi'o has very bad news for you :( Your migration failed, and anvi'o has no backups to restore your "
-                                      "original file. The current artifact is likely in a broken state, and you will unlkely going to be "
+                                      "original file. The current artifact is likely in a broken state, and you will unlikely going to be "
                                       "able to use it. So anvi'o renamed it by adding a prefix '.broken' to its file name. We are very sorry "
                                       "for this error (and anvi'o will certainly not put salt on the wound by reminding you that you could "
                                       "have avoided it by using the `--migrate-safely` flag): \"%s\"." % e)
@@ -301,8 +301,8 @@ if __name__ == '__main__':
                         "all of the files that match to your filters.")
 
     groupB = parser.add_argument_group('SAFETY', "It is up to you. Safe things take much longer and boring. Unsafe things "
-                                                 "are fast, fun, and .. well, don't come to use if your computer loses power "
-                                                 "or somiething.")
+                                                 "are fast, fun, and .. well, don't come to us if your computer loses power "
+                                                 "or something.")
     groupB.add_argument(*anvio.A('migrate-safely'), **anvio.K('migrate-safely'))
     groupB.add_argument(*anvio.A('migrate-quickly'), **anvio.K('migrate-quickly'))