refactor: artifact pruning

lektor_groupby/backref.py

@@ -86,6 +86,7 @@ class VGroups:
         deps = set()  # type: Set[str]
         for vobj in done_list:
             deps.update(vobj.config.dependencies)
+            # ctx.record_virtual_dependency(vobj) # TODO: needed? works without
         for dep in deps:
             ctx.record_dependency(dep)
 

lektor_groupby/plugin.py

@@ -5,7 +5,7 @@ from .backref import GroupByRef, VGroups
 from .groupby import GroupBy
 from .pruner import prune
 from .resolver import Resolver
-from .vobj import VPATH, GroupBySource, GroupByBuildProgram
+from .vobj import GroupBySource, GroupByBuildProgram
 if TYPE_CHECKING:
     from lektor.builder import Builder
     from lektor.sourceobj import SourceObject
@@ -39,7 +39,7 @@ class GroupByPlugin(Plugin):
 
     def on_after_prune(self, builder: 'Builder', **extra: Any) -> None:
         # TODO: find a better way to prune unreferenced elements
-        prune(builder, VPATH, self.resolver.files)
+        prune(builder, self.resolver.files)
 
     # ------------
     #   internal

lektor_groupby/pruner.py

@@ -1,45 +1,77 @@
 '''
-Static collector for build-artifact urls.
-All non-tracked VPATH-urls will be pruned after build.
+Usage:
+  VirtualSourceObject.produce_artifacts()
+    -> remember url and later supply as `current_urls`
+  VirtualSourceObject.build_artifact()
+    -> `get_ctx().record_virtual_dependency(VirtualPruner())`
 '''
 from lektor.reporter import reporter  # report_pruned_artifact
+from lektor.sourceobj import VirtualSourceObject  # subclass
 from lektor.utils import prune_file_and_folder
-from typing import TYPE_CHECKING, Set, Iterable
+import os
+from typing import TYPE_CHECKING, Set, List, Iterable
 if TYPE_CHECKING:
     from lektor.builder import Builder
+    from sqlite3 import Connection
 
 
-def _normalize_url_cache(url_cache: Iterable[str]) -> Set[str]:
+class VirtualPruner(VirtualSourceObject):
+    ''' Indicate that a generated VirtualSourceObject has pruning support. '''
+    VPATH = '/@VirtualPruner'
+
+    def __init__(self) -> None:
+        self._path = VirtualPruner.VPATH  # if needed, add suffix variable
+
+    @property
+    def path(self) -> str:  # type: ignore[override]
+        return self._path
+
+
+def prune(builder: 'Builder', current_urls: Iterable[str]) -> None:
+    ''' Removes previously generated, but now unreferenced Artifacts. '''
+    dest_dir = builder.destination_path
+    con = builder.connect_to_database()
+    try:
+        previous = _query_prunable(con)
+        current = _normalize_urls(current_urls)
+        to_be_pruned = previous.difference(current)
+        for file in to_be_pruned:
+            reporter.report_pruned_artifact(file)  # type: ignore
+            prune_file_and_folder(os.path.join(
+                dest_dir, file.strip('/').replace('/', os.path.sep)), dest_dir)
+        # if no exception raised, update db to remove obsolete references
+        _prune_db_artifacts(con, list(to_be_pruned))
+    finally:
+        con.close()
+
+
+# ---------------------------
+#   Internal helper methods
+# ---------------------------
+
+def _normalize_urls(urls: Iterable[str]) -> Set[str]:
     cache = set()
-    for url in url_cache:
+    for url in urls:
         if url.endswith('/'):
             url += 'index.html'
         cache.add(url.lstrip('/'))
     return cache
 
 
-def prune(builder: 'Builder', vpath: str, url_cache: Iterable[str]) -> None:
-    '''
-    Remove previously generated, unreferenced Artifacts.
-    All urls in url_cache must have a trailing "/index.html" (instead of "/")
-    and also, no leading slash, "blog/index.html" instead of "/blog/index.html"
-    '''
-    vpath = '@' + vpath.lstrip('@')  # just in case of user error
-    dest_path = builder.destination_path
-    url_cache = _normalize_url_cache(url_cache)
-    con = builder.connect_to_database()
-    try:
-        with builder.new_build_state() as build_state:
-            for url, file in build_state.iter_artifacts():
-                if url.lstrip('/') in url_cache:
-                    continue  # generated in this build-run
-                infos = build_state.get_artifact_dependency_infos(url, [])
-                for artifact_name, _ in infos:
-                    if vpath not in artifact_name:
-                        continue  # we only care about our Virtuals
-                    reporter.report_pruned_artifact(url)  # type: ignore
-                    prune_file_and_folder(file.filename, dest_path)
-                    build_state.remove_artifact(url)
-                    break  # there is only one VPATH-entry per source
-    finally:
-        con.close()
+def _query_prunable(conn: 'Connection') -> Set[str]:
+    ''' Query database for artifacts that have the VirtualPruner dependency '''
+    cur = conn.cursor()
+    cur.execute('SELECT artifact FROM artifacts WHERE source = ?',
+                [VirtualPruner.VPATH])
+    return set(x for x, in cur.fetchall())
+
+
+def _prune_db_artifacts(conn: 'Connection', urls: List[str]) -> None:
+    ''' Remove obsolete artifact references from database. '''
+    MAX_VARS = 999  # Default SQLITE_MAX_VARIABLE_NUMBER.
+    cur = conn.cursor()
+    for i in range(0, len(urls), MAX_VARS):
+        batch = urls[i: i + MAX_VARS]
+        cur.execute('DELETE FROM artifacts WHERE artifact in ({})'.format(
+            ','.join(['?'] * len(batch))), batch)
+        conn.commit()

lektor_groupby/vobj.py

@@ -7,6 +7,7 @@ from typing import (
     TYPE_CHECKING, List, Any, Dict, Optional, Generator, Iterator, Iterable
 )
 from .pagination import PaginationConfig
+from .pruner import VirtualPruner
 from .query import FixedRecordsQuery
 from .util import most_used_key, insert_before_ext, build_url, cached_property
 if TYPE_CHECKING:
@@ -250,7 +251,7 @@ class GroupByBuildProgram(BuildProgram):
             self.source.iter_source_filenames()))
 
     def build_artifact(self, artifact: 'Artifact') -> None:
-        get_ctx().record_virtual_dependency(self.source)
+        get_ctx().record_virtual_dependency(VirtualPruner())
         artifact.render_template_into(
             self.source.config.template, this=self.source)