Replace imports/references to swh.model.identifiers, it's deprecated.

swh/scanner/client.py

@@ -16,7 +16,7 @@ from typing import Any, Dict, List, Optional
 
 import aiohttp
 
-from swh.model.identifiers import CoreSWHID
+from swh.model.swhids import CoreSWHID
 
 from .exceptions import error_response
 

swh/scanner/data.py

@@ -8,7 +8,7 @@ from typing import Dict, Optional, Tuple
 
 from swh.model.exceptions import ValidationError
 from swh.model.from_disk import Directory
-from swh.model.identifiers import CONTENT, DIRECTORY, CoreSWHID
+from swh.model.swhids import CoreSWHID
 
 from .client import Client
 
@@ -60,11 +60,11 @@ async def add_origin(source_tree: Directory, data: MerkleNodeInfo, client: Clien
             node_ori = await client.get_origin(node.swhid())
             if node_ori:
                 data[node.swhid()]["origin"] = node_ori
-                if node.object_type == DIRECTORY:
+                if node.object_type == "directory":
                     for sub_node in node.iter_tree():
                         data[sub_node.swhid()]["origin"] = node_ori  # type: ignore
             else:
-                if node.object_type == DIRECTORY:
+                if node.object_type == "directory":
                     children = [sub_node for sub_node in node.iter_tree()]
                     children.remove(node)
                     queue.extend(children)  # type: ignore
@@ -88,7 +88,7 @@ def get_directory_data(
     ):
         directories = list(
             filter(
-                lambda n: n.object_type == DIRECTORY,
+                lambda n: n.object_type == "directory",
                 map(lambda n: n[1], source_tree.items()),
             )
         )
@@ -112,7 +112,7 @@ def directory_content(node: Directory, nodes_data: MerkleNodeInfo) -> Tuple[int,
     """
     known_cnt = 0
     node_contents = list(
-        filter(lambda n: n.object_type == CONTENT, map(lambda n: n[1], node.items()))
+        filter(lambda n: n.object_type == "content", map(lambda n: n[1], node.items()))
     )
     for sub_node in node_contents:
         if nodes_data[sub_node.swhid()]["known"]:
@@ -137,7 +137,7 @@ def get_content_from(
     directory = source_tree[node_path if node_path != source_tree.data["path"] else b""]
     node_contents = list(
         filter(
-            lambda n: n.object_type == CONTENT, map(lambda n: n[1], directory.items())
+            lambda n: n.object_type == "content", map(lambda n: n[1], directory.items())
         )
     )
     files_data = {}

swh/scanner/db.py

@@ -13,18 +13,14 @@ SWHIDs can be added directly from an input file.
 from io import TextIOWrapper
 import logging
 from pathlib import Path
-import re
 import sqlite3
 from typing import Iterable
 
 from swh.core.utils import grouper
+from swh.model.swhids import SWHID_RE
 
 from .exceptions import DBError
 
-# XXX copied and simplified from swh.model.identifiers (WIP), replace this in favor of
-# swh.model.identifiers.SWHID_RE when it is landed there
-SWHID_RE = re.compile("^swh:1:(ori|snp|rel|rev|dir|cnt):[0-9a-f]{40}$")
-
 
 class Db:
     """Local database interface"""

swh/scanner/policy.py

@@ -8,7 +8,6 @@ from typing import no_type_check
 
 from swh.core.utils import grouper
 from swh.model.from_disk import Directory
-from swh.model.identifiers import CONTENT, DIRECTORY
 
 from .client import QUERY_LIMIT, Client
 from .data import MerkleNodeInfo
@@ -56,7 +55,7 @@ class LazyBFS(Policy):
                 self.data[node.swhid()]["known"] = swhids_res[str(node.swhid())][
                     "known"
                 ]
-                if node.object_type == DIRECTORY:
+                if node.object_type == "directory":
                     if not self.data[node.swhid()]["known"]:
                         children = [n[1] for n in list(node.items())]
                         queue.extend(children)
@@ -81,7 +80,7 @@ class GreedyBFS(Policy):
                 seen.append(node)
                 if len(seen) == ssize:
                     return
-                if node.object_type == DIRECTORY and self.data[node.swhid()]["known"]:
+                if node.object_type == "directory" and self.data[node.swhid()]["known"]:
                     sub_nodes = [n for n in node.iter_tree(dedup=False)]
                     sub_nodes.remove(node)  # remove root node
                     for sub_node in sub_nodes:
@@ -117,7 +116,7 @@ class FilePriority(Policy):
         # get all the files
         all_contents = list(
             filter(
-                lambda node: node.object_type == CONTENT, self.source_tree.iter_tree()
+                lambda node: node.object_type == "content", self.source_tree.iter_tree()
             )
         )
         all_contents.reverse()  # check deepest node first
@@ -139,7 +138,7 @@ class FilePriority(Policy):
         # (update children directories accordingly)
         unset_dirs = list(
             filter(
-                lambda node: node.object_type == DIRECTORY
+                lambda node: node.object_type == "directory"
                 and self.data[node.swhid()]["known"] is None,
                 self.source_tree.iter_tree(),
             )
@@ -155,7 +154,7 @@ class FilePriority(Policy):
                 if dir_known:
                     sub_dirs = list(
                         filter(
-                            lambda n: n.object_type == DIRECTORY
+                            lambda n: n.object_type == "directory"
                             and self.data[n.swhid()]["known"] is None,
                             dir_.iter_tree(),
                         )
@@ -177,7 +176,8 @@ class DirectoryPriority(Policy):
         # get all directory contents that have at least one file content
         unknown_dirs = list(
             filter(
-                lambda dir_: dir_.object_type == DIRECTORY and self.has_contents(dir_),
+                lambda dir_: dir_.object_type == "directory"
+                and self.has_contents(dir_),
                 self.source_tree.iter_tree(),
             )
         )
@@ -202,7 +202,7 @@ class DirectoryPriority(Policy):
         # get remaining directories that have no file contents
         empty_dirs = list(
             filter(
-                lambda n: n.object_type == DIRECTORY
+                lambda n: n.object_type == "directory"
                 and not self.has_contents(n)
                 and self.data[n.swhid()]["known"] is None,
                 self.source_tree.iter_tree(),
@@ -220,7 +220,7 @@ class DirectoryPriority(Policy):
         # check unknown file contents
         unknown_cnts = list(
             filter(
-                lambda n: n.object_type == CONTENT
+                lambda n: n.object_type == "content"
                 and self.data[n.swhid()]["known"] is None,
                 self.source_tree.iter_tree(),
             )
@@ -243,7 +243,7 @@ class DirectoryPriority(Policy):
     def get_contents(self, dir_: Directory):
         """Get all the contents of a given directory"""
         for _, node in list(dir_.items()):
-            if node.object_type == CONTENT:
+            if node.object_type == "content":
                 yield node
 
 

swh/scanner/tests/test_client.py

@@ -7,7 +7,7 @@ import json
 
 import pytest
 
-from swh.model.identifiers import CoreSWHID
+from swh.model.swhids import CoreSWHID
 from swh.scanner.client import Client
 from swh.scanner.exceptions import APIError
 

swh/scanner/tests/test_dashboard.py

@@ -5,7 +5,7 @@
 
 import dash_html_components as html
 
-from swh.model.identifiers import CoreSWHID, ObjectType
+from swh.model.swhids import CoreSWHID, ObjectType
 from swh.scanner.dashboard.dashboard import generate_table_body
 from swh.scanner.data import MerkleNodeInfo
 

swh/scanner/tests/test_policy.py

@@ -7,7 +7,7 @@
 from flask import url_for
 import pytest
 
-from swh.model.identifiers import CONTENT, CoreSWHID, ObjectType
+from swh.model.swhids import CoreSWHID, ObjectType
 from swh.scanner.client import Client
 from swh.scanner.data import MerkleNodeInfo, init_merkle_node_info
 from swh.scanner.policy import (
@@ -145,4 +145,4 @@ async def test_greedy_bfs_get_nodes_chunks(live_server, aiosession, big_source_t
         )
     ]
     assert len(chunks) == 2
-    assert chunks[1][-1].object_type == CONTENT
+    assert chunks[1][-1].object_type == "content"