Replace webpub manifest parser with pydantic (PP-1367) (#2163)

Replace our custom web manifest parser with Pydantic models.

I replace the validation we were doing via a patched json schema with the pydantic parser, since it gives better errors and more closely matches what we are expecting in Palace.

bin/opds2_import_monitor

@@ -1,19 +1,13 @@
 #!/usr/bin/env python
 """Update the circulation manager server with new books from OPDS 2.0 import collections."""
-from webpub_manifest_parser.opds2 import OPDS2FeedParserFactory
 
-from palace.manager.core.opds2_import import (
-    OPDS2Importer,
-    OPDS2ImportMonitor,
-    RWPMManifestParser,
-)
+from palace.manager.core.opds2_import import OPDS2Importer, OPDS2ImportMonitor
 from palace.manager.scripts.opds_import import OPDSImportScript
 
 import_script = OPDSImportScript(
     importer_class=OPDS2Importer,
     monitor_class=OPDS2ImportMonitor,
     protocol=OPDS2Importer.NAME,
-    parser=RWPMManifestParser(OPDS2FeedParserFactory()),
 )
 
 import_script.run()

bin/opds2_odl_import_monitor

@@ -3,17 +3,13 @@
 OPDS 2.x + ODL collections."""
 
 
-from webpub_manifest_parser.odl import ODLFeedParserFactory
-
 from palace.manager.api.odl.importer import (
     OPDS2WithODLImporter,
     OPDS2WithODLImportMonitor,
 )
-from palace.manager.core.opds2_import import RWPMManifestParser
 from palace.manager.scripts.monitor import RunCollectionMonitorScript
 
 RunCollectionMonitorScript(
     OPDS2WithODLImportMonitor,
     import_class=OPDS2WithODLImporter,
-    parser=RWPMManifestParser(ODLFeedParserFactory()),
 ).run()

bin/opds2_odl_schema_validate

@@ -3,17 +3,13 @@
 OPDS import collections."""
 
 
-from webpub_manifest_parser.odl import ODLFeedParserFactory
-
 from palace.manager.api.odl.importer import OPDS2WithODLImporter
-from palace.manager.core.opds2_import import RWPMManifestParser
 from palace.manager.core.opds_schema import OPDS2WithODLSchemaValidation
 from palace.manager.scripts.monitor import RunCollectionMonitorScript
 
 import_script = RunCollectionMonitorScript(
     OPDS2WithODLSchemaValidation,
     import_class=OPDS2WithODLImporter,
-    parser=RWPMManifestParser(ODLFeedParserFactory()),
 )
 
 import_script.run()

bin/opds2_reaper_monitor

@@ -6,16 +6,10 @@ from collections.abc import Generator
 from typing import Any, cast
 
 from sqlalchemy.orm import raiseload
-from webpub_manifest_parser.opds2 import OPDS2FeedParserFactory
 
 from palace.manager.core.coverage import CoverageFailure
 from palace.manager.core.metadata_layer import TimestampData
-from palace.manager.core.opds2_import import (
-    OPDS2API,
-    OPDS2Importer,
-    OPDS2ImportMonitor,
-    RWPMManifestParser,
-)
+from palace.manager.core.opds2_import import OPDS2API, OPDS2Importer, OPDS2ImportMonitor
 from palace.manager.scripts.input import CollectionInputScript
 from palace.manager.sqlalchemy.model.collection import Collection
 from palace.manager.sqlalchemy.model.edition import Edition
@@ -28,7 +22,6 @@ def main():
         importer_class=OPDS2Importer,
         monitor_class=OPDS2ReaperMonitor,
         protocol=OPDS2Importer.NAME,
-        parser=RWPMManifestParser(OPDS2FeedParserFactory()),
     )
 
     reaper_script.run()

bin/opds2_schema_validate

@@ -2,18 +2,14 @@
 """Update the circulation manager server with new books from
 OPDS import collections."""
 
-
-from webpub_manifest_parser.opds2 import OPDS2FeedParserFactory
-
-from palace.manager.core.opds2_import import OPDS2Importer, RWPMManifestParser
+from palace.manager.core.opds2_import import OPDS2Importer
 from palace.manager.core.opds_schema import OPDS2SchemaValidation
 from palace.manager.scripts.opds_import import OPDSImportScript
 
 import_script = OPDSImportScript(
     importer_class=OPDS2Importer,
     monitor_class=OPDS2SchemaValidation,
     protocol=OPDS2Importer.NAME,
-    parser=RWPMManifestParser(OPDS2FeedParserFactory()),
 )
 
 import_script.run()

pyproject.toml

@@ -100,6 +100,7 @@ module = [
     "palace.manager.api.opds_for_distributors",
     "palace.manager.core.opds2_import",
     "palace.manager.core.opds_import",
+    "palace.manager.core.opds_schema",
     "palace.manager.core.selftest",
     "palace.manager.feed.*",
     "palace.manager.integration.*",
@@ -198,7 +199,6 @@ module = [
     "unicodecsv",
     "uwsgi",
     "wcag_contrast_ratio",
-    "webpub_manifest_parser.*",
 ]
 
 [tool.poetry]
@@ -243,7 +243,6 @@ multipledispatch = "^1.0"
 nameparser = "^1.1"  # nameparser is for author name manipulations
 opensearch-dsl = "~1.0"
 opensearch-py = "~1.1"
-palace-webpub-manifest-parser = "^4.0.0"
 pillow = "^11.0"
 pycountry = "^24.6.1"
 pycryptodome = "^3.18"