Fix identity reconstruction metadata loss with v2 schema
Implements identities.json v2 schema with embedded video metadata to fix duplicate resolution by quality, which previously failed due to VideoFile objects being reconstructed with hardcoded defaults (size_bytes=0, resolution=None, codec=None). Changes: - Add --inventory flag to vlm parse command to embed video metadata - Update _video_file_from_record() to extract embedded metadata if present - Add vlm_schema_version field to identities.json (v1.0 or v2.0) - Maintain backward compatibility with v1 files (no metadata) Schema v2 format: - Embeds video_metadata object in each record (movies/series) - Contains: size_bytes, modified_timestamp, resolution, codec, duration_seconds, bitrate_kbps - Enables accurate quality comparison during duplicate analysis Testing: - Added comprehensive unit tests for io.py functions - Added CLI integration tests for parse command - Added end-to-end tests for duplicate quality comparison - All 437 existing tests still pass (1 pre-existing failure in executor) Documentation: - Updated README.md with --inventory usage examples - Updated CLAUDE.md with schema versioning details - Added workflow examples showing metadata embedding This fix resolves the critical P0 issue where duplicate resolution by_quality strategy failed completely due to missing video metadata in reconstructed VideoFile objects. Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
windyboy
co-authored by
Claude Sonnet 4.5
Claude Sonnet 4.5
parent
1f55eab304
commit
065195b83b
@@ -0,0 +1,171 @@
|
||||
"""Tests for the parse CLI command."""
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
from click.testing import CliRunner
|
||||
|
||||
from vlm.cli import main
|
||||
|
||||
|
||||
class TestParseCommand:
|
||||
"""Tests for vlm parse command."""
|
||||
|
||||
def test_parse_without_inventory_v1_schema(self, tmp_path):
|
||||
"""Test parse without --inventory flag produces v1 schema."""
|
||||
# Create a simple inventory CSV (without metadata)
|
||||
inventory_csv = tmp_path / "inventory.csv"
|
||||
inventory_csv.write_text(
|
||||
"# vlm inventory\n"
|
||||
"path,filename,size_bytes,modified_timestamp,category,resolution,codec,duration_seconds,bitrate_kbps\n"
|
||||
"/library/movie/Matrix (1999).mkv,Matrix (1999).mkv,1000000,2024-01-01T00:00:00,movie,,,\n"
|
||||
"/library/series/Breaking Bad S01E01.mkv,Breaking Bad S01E01.mkv,500000,2024-01-02T00:00:00,series,,,\n"
|
||||
)
|
||||
|
||||
output_json = tmp_path / "identities.json"
|
||||
|
||||
runner = CliRunner()
|
||||
result = runner.invoke(
|
||||
main,
|
||||
[
|
||||
"--config",
|
||||
str(tmp_path / "config.yaml"),
|
||||
"parse",
|
||||
"--input",
|
||||
str(inventory_csv),
|
||||
"--output",
|
||||
str(output_json),
|
||||
],
|
||||
)
|
||||
|
||||
# Command should succeed
|
||||
assert result.exit_code == 0
|
||||
|
||||
# Load output and verify v1 schema (no version field or version is 1.0)
|
||||
with open(output_json) as f:
|
||||
data = json.load(f)
|
||||
|
||||
# v1 schema - no vlm_schema_version or it's "1.0"
|
||||
assert data.get("vlm_schema_version", "1.0") == "1.0"
|
||||
|
||||
# Verify no video_metadata in records
|
||||
if data.get("movies"):
|
||||
for movie in data["movies"]:
|
||||
assert "video_metadata" not in movie
|
||||
if data.get("series"):
|
||||
for series in data["series"]:
|
||||
assert "video_metadata" not in series
|
||||
|
||||
def test_parse_with_inventory_v2_schema(self, tmp_path):
|
||||
"""Test parse with --inventory flag produces v2 schema with embedded metadata."""
|
||||
# Create inventory CSV with full metadata
|
||||
inventory_csv = tmp_path / "inventory.csv"
|
||||
inventory_csv.write_text(
|
||||
"# vlm inventory\n"
|
||||
"path,filename,size_bytes,modified_timestamp,category,resolution,codec,duration_seconds,bitrate_kbps\n"
|
||||
"/library/movie/Matrix (1999).mkv,Matrix (1999).mkv,2000000000,2024-01-01T10:00:00+00:00,movie,1920x1080,h264,7200.5,5000\n"
|
||||
"/library/series/Breaking Bad S01E01.mkv,Breaking Bad S01E01.mkv,500000000,2024-01-02T15:00:00+00:00,series,1280x720,h264,2700.0,3000\n"
|
||||
)
|
||||
|
||||
output_json = tmp_path / "identities.json"
|
||||
|
||||
runner = CliRunner()
|
||||
result = runner.invoke(
|
||||
main,
|
||||
[
|
||||
"--config",
|
||||
str(tmp_path / "config.yaml"),
|
||||
"parse",
|
||||
"--input",
|
||||
str(inventory_csv),
|
||||
"--output",
|
||||
str(output_json),
|
||||
"--inventory",
|
||||
str(inventory_csv),
|
||||
],
|
||||
)
|
||||
|
||||
# Command should succeed
|
||||
assert result.exit_code == 0
|
||||
assert "Loading video metadata from:" in result.output
|
||||
assert "Loaded metadata for 2 files" in result.output
|
||||
|
||||
# Load output and verify v2 schema
|
||||
with open(output_json) as f:
|
||||
data = json.load(f)
|
||||
|
||||
# v2 schema version
|
||||
assert data["vlm_schema_version"] == "2.0"
|
||||
|
||||
# Verify video_metadata embedded in movie record
|
||||
assert len(data["movies"]) == 1
|
||||
movie = data["movies"][0]
|
||||
assert "video_metadata" in movie
|
||||
assert movie["video_metadata"]["size_bytes"] == 2000000000
|
||||
assert movie["video_metadata"]["resolution"] == "1920x1080"
|
||||
assert movie["video_metadata"]["codec"] == "h264"
|
||||
assert movie["video_metadata"]["duration_seconds"] == 7200.5
|
||||
assert movie["video_metadata"]["bitrate_kbps"] == 5000
|
||||
|
||||
# Verify video_metadata embedded in series record
|
||||
assert len(data["series"]) == 1
|
||||
series = data["series"][0]
|
||||
assert "video_metadata" in series
|
||||
assert series["video_metadata"]["size_bytes"] == 500000000
|
||||
assert series["video_metadata"]["resolution"] == "1280x720"
|
||||
assert series["video_metadata"]["codec"] == "h264"
|
||||
assert series["video_metadata"]["duration_seconds"] == 2700.0
|
||||
assert series["video_metadata"]["bitrate_kbps"] == 3000
|
||||
|
||||
def test_parse_with_inventory_partial_metadata(self, tmp_path):
|
||||
"""Test parse with inventory that has partial metadata."""
|
||||
# Create inventory with some files having metadata, some not
|
||||
inventory_csv = tmp_path / "inventory.csv"
|
||||
inventory_csv.write_text(
|
||||
"# vlm inventory\n"
|
||||
"path,filename,size_bytes,modified_timestamp,category,resolution,codec,duration_seconds,bitrate_kbps\n"
|
||||
"/library/movie/Matrix (1999).mkv,Matrix (1999).mkv,2000000000,2024-01-01T10:00:00+00:00,movie,1920x1080,h264,,\n"
|
||||
"/library/movie/Inception (2010).mkv,Inception (2010).mkv,1500000000,2024-01-02T10:00:00+00:00,movie,,,\n"
|
||||
)
|
||||
|
||||
output_json = tmp_path / "identities.json"
|
||||
|
||||
runner = CliRunner()
|
||||
result = runner.invoke(
|
||||
main,
|
||||
[
|
||||
"--config",
|
||||
str(tmp_path / "config.yaml"),
|
||||
"parse",
|
||||
"--input",
|
||||
str(inventory_csv),
|
||||
"--output",
|
||||
str(output_json),
|
||||
"--inventory",
|
||||
str(inventory_csv),
|
||||
],
|
||||
)
|
||||
|
||||
# Command should succeed
|
||||
assert result.exit_code == 0
|
||||
|
||||
# Load output and verify
|
||||
with open(output_json) as f:
|
||||
data = json.load(f)
|
||||
|
||||
assert data["vlm_schema_version"] == "2.0"
|
||||
assert len(data["movies"]) == 2
|
||||
|
||||
# First movie has partial metadata
|
||||
movie1 = data["movies"][0]
|
||||
assert movie1["video_metadata"]["size_bytes"] == 2000000000
|
||||
assert movie1["video_metadata"]["resolution"] == "1920x1080"
|
||||
assert movie1["video_metadata"]["codec"] == "h264"
|
||||
assert movie1["video_metadata"]["duration_seconds"] is None
|
||||
assert movie1["video_metadata"]["bitrate_kbps"] is None
|
||||
|
||||
# Second movie has minimal metadata
|
||||
movie2 = data["movies"][1]
|
||||
assert movie2["video_metadata"]["size_bytes"] == 1500000000
|
||||
assert movie2["video_metadata"]["resolution"] is None
|
||||
assert movie2["video_metadata"]["codec"] is None
|
||||
@@ -0,0 +1,252 @@
|
||||
"""Integration tests for duplicate resolution with embedded video metadata."""
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from vlm.io import load_identities_json, identities_to_analysis_input
|
||||
from vlm.analysis import detect_duplicates
|
||||
|
||||
|
||||
class TestDuplicateQualityWithMetadata:
|
||||
"""Test that embedded metadata enables accurate quality comparison."""
|
||||
|
||||
def test_duplicate_quality_comparison_with_v2_metadata(self, tmp_path):
|
||||
"""Test that v2 identities with embedded metadata produce accurate quality comparison."""
|
||||
# Create v2 identities.json with two duplicates having different quality
|
||||
identities_file = tmp_path / "identities.json"
|
||||
data = {
|
||||
"vlm_schema_version": "2.0",
|
||||
"metadata": {
|
||||
"generated": "2024-02-13T12:00:00",
|
||||
"source_inventory": "inventory.csv",
|
||||
"total_files": 2,
|
||||
},
|
||||
"movies": [
|
||||
{
|
||||
"path": "/library/movie/Matrix (1999) 1080p.mkv",
|
||||
"filename": "Matrix (1999) 1080p.mkv",
|
||||
"category": "movie",
|
||||
"title": "The Matrix",
|
||||
"year": 1999,
|
||||
"confidence": 0.9,
|
||||
"needs_review": False,
|
||||
"video_metadata": {
|
||||
"size_bytes": 2000000000,
|
||||
"modified_timestamp": "2024-01-01T10:00:00+00:00",
|
||||
"resolution": "1920x1080",
|
||||
"codec": "h264",
|
||||
"duration_seconds": 7200.0,
|
||||
"bitrate_kbps": 5000,
|
||||
},
|
||||
},
|
||||
{
|
||||
"path": "/library/movie/Matrix (1999) 720p.mkv",
|
||||
"filename": "Matrix (1999) 720p.mkv",
|
||||
"category": "movie",
|
||||
"title": "The Matrix",
|
||||
"year": 1999,
|
||||
"confidence": 0.9,
|
||||
"needs_review": False,
|
||||
"video_metadata": {
|
||||
"size_bytes": 1000000000,
|
||||
"modified_timestamp": "2024-01-02T10:00:00+00:00",
|
||||
"resolution": "1280x720",
|
||||
"codec": "h264",
|
||||
"duration_seconds": 7200.0,
|
||||
"bitrate_kbps": 2500,
|
||||
},
|
||||
},
|
||||
],
|
||||
"series": [],
|
||||
"anime": [],
|
||||
"other": [],
|
||||
}
|
||||
|
||||
# Save identities
|
||||
with open(identities_file, "w") as f:
|
||||
json.dump(data, f, indent=2)
|
||||
|
||||
# Load identities
|
||||
loaded = load_identities_json(identities_file)
|
||||
|
||||
# Convert to analysis input
|
||||
movie_identities, series_identities, video_files = identities_to_analysis_input(loaded)
|
||||
|
||||
# Create identity-file pairs
|
||||
identity_file_pairs = list(zip(movie_identities, video_files))
|
||||
|
||||
# Detect duplicates
|
||||
duplicates = detect_duplicates(identity_file_pairs)
|
||||
|
||||
# Verify we found 1 duplicate group
|
||||
assert len(duplicates) == 1
|
||||
duplicate_group = duplicates[0]
|
||||
|
||||
# Verify duplicate group has 2 files
|
||||
assert len(duplicate_group.files) == 2
|
||||
|
||||
# Verify quality comparison has actual metadata (not zeros/nulls)
|
||||
quality_comparison = duplicate_group.quality_comparison
|
||||
assert len(quality_comparison) == 2
|
||||
|
||||
# First file (1080p) should have correct metadata
|
||||
file1 = quality_comparison[0]
|
||||
assert file1["size_bytes"] == 2000000000
|
||||
assert file1["resolution"] == "1920x1080"
|
||||
assert file1["codec"] == "h264"
|
||||
assert file1["bitrate_kbps"] == 5000
|
||||
|
||||
# Second file (720p) should have correct metadata
|
||||
file2 = quality_comparison[1]
|
||||
assert file2["size_bytes"] == 1000000000
|
||||
assert file2["resolution"] == "1280x720"
|
||||
assert file2["codec"] == "h264"
|
||||
assert file2["bitrate_kbps"] == 2500
|
||||
|
||||
def test_duplicate_quality_comparison_with_v1_no_metadata(self, tmp_path):
|
||||
"""Test that v1 identities without metadata produce limited quality comparison."""
|
||||
# Create v1 identities.json without embedded metadata (backward compatibility)
|
||||
identities_file = tmp_path / "identities.json"
|
||||
data = {
|
||||
# No vlm_schema_version (v1)
|
||||
"metadata": {
|
||||
"generated": "2024-02-13T12:00:00",
|
||||
"source_inventory": "inventory.csv",
|
||||
"total_files": 2,
|
||||
},
|
||||
"movies": [
|
||||
{
|
||||
"path": "/library/movie/Inception (2010) 1080p.mkv",
|
||||
"filename": "Inception (2010) 1080p.mkv",
|
||||
"category": "movie",
|
||||
"title": "Inception",
|
||||
"year": 2010,
|
||||
"confidence": 0.9,
|
||||
"needs_review": False,
|
||||
# No video_metadata
|
||||
},
|
||||
{
|
||||
"path": "/library/movie/Inception (2010) 720p.mkv",
|
||||
"filename": "Inception (2010) 720p.mkv",
|
||||
"category": "movie",
|
||||
"title": "Inception",
|
||||
"year": 2010,
|
||||
"confidence": 0.9,
|
||||
"needs_review": False,
|
||||
# No video_metadata
|
||||
},
|
||||
],
|
||||
"series": [],
|
||||
"anime": [],
|
||||
"other": [],
|
||||
}
|
||||
|
||||
# Save identities
|
||||
with open(identities_file, "w") as f:
|
||||
json.dump(data, f, indent=2)
|
||||
|
||||
# Load identities
|
||||
loaded = load_identities_json(identities_file)
|
||||
|
||||
# Convert to analysis input
|
||||
movie_identities, series_identities, video_files = identities_to_analysis_input(loaded)
|
||||
|
||||
# Create identity-file pairs
|
||||
identity_file_pairs = list(zip(movie_identities, video_files))
|
||||
|
||||
# Detect duplicates
|
||||
duplicates = detect_duplicates(identity_file_pairs)
|
||||
|
||||
# Verify we found 1 duplicate group
|
||||
assert len(duplicates) == 1
|
||||
duplicate_group = duplicates[0]
|
||||
|
||||
# Verify quality comparison exists but has limited data (v1 defaults)
|
||||
quality_comparison = duplicate_group.quality_comparison
|
||||
assert len(quality_comparison) == 2
|
||||
|
||||
# v1 files have size_bytes=0 and no resolution/codec
|
||||
for quality_info in quality_comparison:
|
||||
assert quality_info["size_bytes"] == 0
|
||||
assert "resolution" not in quality_info # None values are not included
|
||||
assert "codec" not in quality_info
|
||||
|
||||
def test_series_duplicate_quality_comparison_with_v2_metadata(self, tmp_path):
|
||||
"""Test series duplicates with embedded metadata."""
|
||||
identities_file = tmp_path / "identities.json"
|
||||
data = {
|
||||
"vlm_schema_version": "2.0",
|
||||
"metadata": {
|
||||
"generated": "2024-02-13T12:00:00",
|
||||
"source_inventory": "inventory.csv",
|
||||
"total_files": 2,
|
||||
},
|
||||
"movies": [],
|
||||
"series": [
|
||||
{
|
||||
"path": "/library/series/Breaking Bad S01E01 1080p.mkv",
|
||||
"filename": "Breaking Bad S01E01 1080p.mkv",
|
||||
"category": "series",
|
||||
"title": "Breaking Bad",
|
||||
"season": 1,
|
||||
"episodes": [1],
|
||||
"confidence": 0.9,
|
||||
"needs_review": False,
|
||||
"video_metadata": {
|
||||
"size_bytes": 800000000,
|
||||
"modified_timestamp": "2024-01-01T10:00:00+00:00",
|
||||
"resolution": "1920x1080",
|
||||
"codec": "hevc",
|
||||
"duration_seconds": 2700.0,
|
||||
"bitrate_kbps": 4000,
|
||||
},
|
||||
},
|
||||
{
|
||||
"path": "/library/series/Breaking Bad S01E01 720p.mkv",
|
||||
"filename": "Breaking Bad S01E01 720p.mkv",
|
||||
"category": "series",
|
||||
"title": "Breaking Bad",
|
||||
"season": 1,
|
||||
"episodes": [1],
|
||||
"confidence": 0.9,
|
||||
"needs_review": False,
|
||||
"video_metadata": {
|
||||
"size_bytes": 400000000,
|
||||
"modified_timestamp": "2024-01-02T10:00:00+00:00",
|
||||
"resolution": "1280x720",
|
||||
"codec": "h264",
|
||||
"duration_seconds": 2700.0,
|
||||
"bitrate_kbps": 2000,
|
||||
},
|
||||
},
|
||||
],
|
||||
"anime": [],
|
||||
"other": [],
|
||||
}
|
||||
|
||||
# Save and load
|
||||
with open(identities_file, "w") as f:
|
||||
json.dump(data, f, indent=2)
|
||||
|
||||
loaded = load_identities_json(identities_file)
|
||||
movie_identities, series_identities, video_files = identities_to_analysis_input(loaded)
|
||||
|
||||
# Create identity-file pairs for series
|
||||
identity_file_pairs = list(zip(series_identities, video_files))
|
||||
|
||||
# Detect duplicates
|
||||
duplicates = detect_duplicates(identity_file_pairs)
|
||||
|
||||
# Verify duplicate detected
|
||||
assert len(duplicates) == 1
|
||||
duplicate_group = duplicates[0]
|
||||
assert len(duplicate_group.files) == 2
|
||||
|
||||
# Verify quality comparison has metadata
|
||||
quality_comparison = duplicate_group.quality_comparison
|
||||
assert quality_comparison[0]["resolution"] == "1920x1080"
|
||||
assert quality_comparison[0]["codec"] == "hevc"
|
||||
assert quality_comparison[1]["resolution"] == "1280x720"
|
||||
assert quality_comparison[1]["codec"] == "h264"
|
||||
@@ -0,0 +1,262 @@
|
||||
"""Tests for the I/O layer module."""
|
||||
|
||||
import json
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from vlm.io import (
|
||||
_video_file_from_record,
|
||||
load_identities_json,
|
||||
save_identities_json,
|
||||
)
|
||||
from vlm.models import VideoFile
|
||||
|
||||
|
||||
class TestVideoFileFromRecord:
|
||||
"""Tests for _video_file_from_record function."""
|
||||
|
||||
def test_video_file_from_record_with_metadata_v2(self):
|
||||
"""Test loading VideoFile from v2 record with embedded metadata."""
|
||||
record = {
|
||||
"path": "/library/movie/The Matrix (1999).mkv",
|
||||
"filename": "The Matrix (1999).mkv",
|
||||
"category": "movie",
|
||||
"title": "The Matrix",
|
||||
"year": 1999,
|
||||
"confidence": 0.9,
|
||||
"needs_review": False,
|
||||
"video_metadata": {
|
||||
"size_bytes": 1234567890,
|
||||
"modified_timestamp": "2024-01-01T10:00:00+00:00",
|
||||
"resolution": "1920x1080",
|
||||
"codec": "h264",
|
||||
"duration_seconds": 7200.5,
|
||||
"bitrate_kbps": 5000,
|
||||
},
|
||||
}
|
||||
|
||||
vf = _video_file_from_record(record)
|
||||
|
||||
assert vf.path == Path("/library/movie/The Matrix (1999).mkv")
|
||||
assert vf.filename == "The Matrix (1999).mkv"
|
||||
assert vf.category == "movie"
|
||||
assert vf.size_bytes == 1234567890
|
||||
assert vf.resolution == "1920x1080"
|
||||
assert vf.codec == "h264"
|
||||
assert vf.duration_seconds == 7200.5
|
||||
assert vf.bitrate_kbps == 5000
|
||||
assert isinstance(vf.modified_timestamp, datetime)
|
||||
|
||||
def test_video_file_from_record_without_metadata_v1(self):
|
||||
"""Test loading VideoFile from v1 record without metadata (backward compatibility)."""
|
||||
record = {
|
||||
"path": "/library/movie/Inception (2010).mkv",
|
||||
"filename": "Inception (2010).mkv",
|
||||
"category": "movie",
|
||||
"title": "Inception",
|
||||
"year": 2010,
|
||||
"confidence": 0.9,
|
||||
"needs_review": False,
|
||||
}
|
||||
|
||||
vf = _video_file_from_record(record)
|
||||
|
||||
assert vf.path == Path("/library/movie/Inception (2010).mkv")
|
||||
assert vf.filename == "Inception (2010).mkv"
|
||||
assert vf.category == "movie"
|
||||
# v1 defaults
|
||||
assert vf.size_bytes == 0
|
||||
assert vf.resolution is None
|
||||
assert vf.codec is None
|
||||
assert vf.duration_seconds is None
|
||||
assert vf.bitrate_kbps is None
|
||||
assert isinstance(vf.modified_timestamp, datetime)
|
||||
|
||||
def test_video_file_from_record_partial_metadata(self):
|
||||
"""Test loading VideoFile with partial metadata (some fields missing)."""
|
||||
record = {
|
||||
"path": "/library/series/Breaking Bad S01E01.mkv",
|
||||
"filename": "Breaking Bad S01E01.mkv",
|
||||
"category": "series",
|
||||
"title": "Breaking Bad",
|
||||
"season": 1,
|
||||
"episodes": [1],
|
||||
"confidence": 0.9,
|
||||
"needs_review": False,
|
||||
"video_metadata": {
|
||||
"size_bytes": 987654321,
|
||||
"modified_timestamp": "2024-02-01T15:30:00+00:00",
|
||||
"resolution": "1280x720",
|
||||
# codec missing
|
||||
# duration_seconds missing
|
||||
# bitrate_kbps missing
|
||||
},
|
||||
}
|
||||
|
||||
vf = _video_file_from_record(record)
|
||||
|
||||
assert vf.size_bytes == 987654321
|
||||
assert vf.resolution == "1280x720"
|
||||
assert vf.codec is None
|
||||
assert vf.duration_seconds is None
|
||||
assert vf.bitrate_kbps is None
|
||||
|
||||
|
||||
class TestIdentitiesJsonVersioning:
|
||||
"""Tests for identities.json schema versioning."""
|
||||
|
||||
def test_load_identities_v2_with_metadata(self, tmp_path):
|
||||
"""Test loading v2 identities.json with video metadata."""
|
||||
identities_file = tmp_path / "identities.json"
|
||||
data = {
|
||||
"vlm_schema_version": "2.0",
|
||||
"metadata": {
|
||||
"generated": "2024-01-01T10:00:00",
|
||||
"source_inventory": "inventory.csv",
|
||||
"total_files": 1,
|
||||
},
|
||||
"movies": [
|
||||
{
|
||||
"path": "/library/movie/Test (2024).mkv",
|
||||
"filename": "Test (2024).mkv",
|
||||
"category": "movie",
|
||||
"title": "Test",
|
||||
"year": 2024,
|
||||
"confidence": 0.9,
|
||||
"needs_review": False,
|
||||
"video_metadata": {
|
||||
"size_bytes": 1000000,
|
||||
"modified_timestamp": "2024-01-01T00:00:00+00:00",
|
||||
"resolution": "1920x1080",
|
||||
"codec": "h264",
|
||||
"duration_seconds": 3600.0,
|
||||
"bitrate_kbps": 2500,
|
||||
},
|
||||
}
|
||||
],
|
||||
"series": [],
|
||||
"anime": [],
|
||||
"other": [],
|
||||
}
|
||||
|
||||
save_identities_json(data, identities_file)
|
||||
loaded = load_identities_json(identities_file)
|
||||
|
||||
assert loaded["vlm_schema_version"] == "2.0"
|
||||
assert len(loaded["movies"]) == 1
|
||||
assert "video_metadata" in loaded["movies"][0]
|
||||
assert loaded["movies"][0]["video_metadata"]["size_bytes"] == 1000000
|
||||
|
||||
def test_load_identities_v1_backward_compatibility(self, tmp_path):
|
||||
"""Test loading v1 identities.json without version field (backward compatibility)."""
|
||||
identities_file = tmp_path / "identities.json"
|
||||
data = {
|
||||
# No vlm_schema_version field (v1)
|
||||
"metadata": {
|
||||
"generated": "2024-01-01T10:00:00",
|
||||
"source_inventory": "inventory.csv",
|
||||
"total_files": 1,
|
||||
},
|
||||
"movies": [
|
||||
{
|
||||
"path": "/library/movie/Old (2023).mkv",
|
||||
"filename": "Old (2023).mkv",
|
||||
"category": "movie",
|
||||
"title": "Old",
|
||||
"year": 2023,
|
||||
"confidence": 0.9,
|
||||
"needs_review": False,
|
||||
# No video_metadata field
|
||||
}
|
||||
],
|
||||
"series": [],
|
||||
"anime": [],
|
||||
"other": [],
|
||||
}
|
||||
|
||||
save_identities_json(data, identities_file)
|
||||
loaded = load_identities_json(identities_file)
|
||||
|
||||
# v1 files don't have version field
|
||||
assert "vlm_schema_version" not in loaded or loaded.get("vlm_schema_version") is None
|
||||
assert len(loaded["movies"]) == 1
|
||||
assert "video_metadata" not in loaded["movies"][0]
|
||||
|
||||
|
||||
class TestIdentitiesJsonRoundTrip:
|
||||
"""Tests for identities.json save/load round-trip."""
|
||||
|
||||
def test_save_and_load_v2_identities(self, tmp_path):
|
||||
"""Test saving and loading v2 identities with metadata."""
|
||||
identities_file = tmp_path / "identities_v2.json"
|
||||
original_data = {
|
||||
"vlm_schema_version": "2.0",
|
||||
"metadata": {
|
||||
"generated": "2024-02-13T12:00:00",
|
||||
"source_inventory": "test_inventory.csv",
|
||||
"total_files": 2,
|
||||
},
|
||||
"movies": [
|
||||
{
|
||||
"path": "/library/movie/Movie1 (2024).mkv",
|
||||
"filename": "Movie1 (2024).mkv",
|
||||
"category": "movie",
|
||||
"title": "Movie1",
|
||||
"year": 2024,
|
||||
"confidence": 0.9,
|
||||
"needs_review": False,
|
||||
"video_metadata": {
|
||||
"size_bytes": 2000000000,
|
||||
"modified_timestamp": "2024-02-10T08:00:00+00:00",
|
||||
"resolution": "3840x2160",
|
||||
"codec": "hevc",
|
||||
"duration_seconds": 7200.0,
|
||||
"bitrate_kbps": 8000,
|
||||
},
|
||||
}
|
||||
],
|
||||
"series": [
|
||||
{
|
||||
"path": "/library/series/Show S01E01.mkv",
|
||||
"filename": "Show S01E01.mkv",
|
||||
"category": "series",
|
||||
"title": "Show",
|
||||
"season": 1,
|
||||
"episodes": [1],
|
||||
"confidence": 0.9,
|
||||
"needs_review": False,
|
||||
"video_metadata": {
|
||||
"size_bytes": 500000000,
|
||||
"modified_timestamp": "2024-02-11T10:00:00+00:00",
|
||||
"resolution": "1920x1080",
|
||||
"codec": "h264",
|
||||
"duration_seconds": 2700.0,
|
||||
"bitrate_kbps": 3000,
|
||||
},
|
||||
}
|
||||
],
|
||||
"anime": [],
|
||||
"other": [],
|
||||
}
|
||||
|
||||
save_identities_json(original_data, identities_file)
|
||||
loaded_data = load_identities_json(identities_file)
|
||||
|
||||
# Verify structure
|
||||
assert loaded_data["vlm_schema_version"] == "2.0"
|
||||
assert len(loaded_data["movies"]) == 1
|
||||
assert len(loaded_data["series"]) == 1
|
||||
|
||||
# Verify movie metadata preserved
|
||||
movie = loaded_data["movies"][0]
|
||||
assert movie["video_metadata"]["size_bytes"] == 2000000000
|
||||
assert movie["video_metadata"]["resolution"] == "3840x2160"
|
||||
assert movie["video_metadata"]["codec"] == "hevc"
|
||||
|
||||
# Verify series metadata preserved
|
||||
series = loaded_data["series"][0]
|
||||
assert series["video_metadata"]["size_bytes"] == 500000000
|
||||
assert series["video_metadata"]["resolution"] == "1920x1080"
|
||||
assert series["video_metadata"]["codec"] == "h264"
|
||||
Reference in New Issue
Block a user