photo-stack-finder 0.1.7__py3-none-any.whl → 0.1.8__py3-none-any.whl

orchestrator/review_persistence.py

@@ -1,162 +1,162 @@
-"""Functions for persisting and loading review decisions."""
-
-from __future__ import annotations
-
-import csv
-import json
-from pathlib import Path
-from typing import Any
-
-from utils.review_types import (
-    DeletionIndexEntry,
-    IdenticalDecision,
-    PhotoIdentifier,
-    ReviewIndexEntry,
-    SequenceDecision,
-)
-
-
-def append_decision_to_log(decision: IdenticalDecision | SequenceDecision, work_dir: Path) -> None:
-    """Append a review decision to the JSONL log.
-
-    Args:
-        decision: Decision object (IdenticalDecision or SequenceDecision)
-        work_dir: Work directory containing the log file
-    """
-    log_path: Path = work_dir / "review_decisions.jsonl"
-
-    # Ensure work directory exists
-    work_dir.mkdir(parents=True, exist_ok=True)
-
-    # Append decision as JSON line
-    with log_path.open("a", encoding="utf-8") as f:
-        json.dump(decision, f, ensure_ascii=False)
-        f.write("\n")
-
-
-def build_review_index(work_dir: Path) -> dict[str, Any]:
-    """Build in-memory indices from JSONL log and generate CSV files.
-
-    Reads review_decisions.jsonl and creates:
-    - review_index_identical.csv: identical group decisions
-    - review_index_sequences.csv: sequence group decisions
-    - review_index_deletions.csv: individual photo deletions
-
-    Args:
-        work_dir: Work directory containing the log file
-
-    Returns:
-        Dictionary with 'identical', 'sequences', and 'deletions' indices
-    """
-    log_path: Path = work_dir / "review_decisions.jsonl"
-
-    if not log_path.exists():
-        # No decisions yet, return empty indices
-        return {"identical": {}, "sequences": {}, "deletions": {}}
-
-    # Parse JSONL log
-    identical_index: dict[str, ReviewIndexEntry] = {}
-    sequences_index: dict[str, ReviewIndexEntry] = {}
-    deletions_index: dict[PhotoIdentifier, DeletionIndexEntry] = {}
-
-    with log_path.open(encoding="utf-8") as f:
-        for _line_num, raw_line in enumerate(f, 1):
-            line = raw_line.strip()
-            if not line:
-                continue
-
-            try:
-                decision: dict[str, Any] = json.loads(line)
-                decision_type: str | None = decision.get("type")
-
-                if decision_type == "identical":
-                    # Index identical group decision
-                    group_id: str = decision["group_id"]
-                    identical_index[group_id] = {
-                        "group_id": group_id,
-                        "decision_type": "identical",
-                        "action": decision["action"],
-                        "timestamp": decision["timestamp"],
-                        "user": decision["user"],
-                    }
-
-                    # Index deletions
-                    deleted_photos: list[tuple[str, str]] = decision.get("deleted_photos", [])
-                    sha256: str
-                    path: str
-                    for sha256, path in deleted_photos:
-                        deletions_index[(sha256, path)] = {
-                            "sha256": sha256,
-                            "path": path,
-                            "reason": "identical_group",
-                            "group_id": group_id,
-                            "timestamp": decision["timestamp"],
-                            "user": decision["user"],
-                        }
-
-                elif decision_type == "sequences":
-                    # Index sequence group decision
-                    seq_group_id: str = decision["group_id"]
-                    sequences_index[seq_group_id] = {
-                        "group_id": seq_group_id,
-                        "decision_type": "sequences",
-                        "action": decision["action"],
-                        "timestamp": decision["timestamp"],
-                        "user": decision["user"],
-                    }
-
-                    # Index deletions
-                    seq_deleted_photos: list[tuple[str, str]] = decision.get("deleted_photos", [])
-                    seq_sha256: str
-                    seq_path: str
-                    for seq_sha256, seq_path in seq_deleted_photos:
-                        deletions_index[(seq_sha256, seq_path)] = {
-                            "sha256": seq_sha256,
-                            "path": seq_path,
-                            "reason": "sequence_group",
-                            "group_id": seq_group_id,
-                            "timestamp": decision["timestamp"],
-                            "user": decision["user"],
-                        }
-
-            except json.JSONDecodeError:
-                continue
-
-    # Write CSV indices
-    _write_csv_index(
-        work_dir / "review_index_identical.csv",
-        identical_index.values(),
-        ["group_id", "decision_type", "action", "timestamp", "user"],
-    )
-
-    _write_csv_index(
-        work_dir / "review_index_sequences.csv",
-        sequences_index.values(),
-        ["group_id", "decision_type", "action", "timestamp", "user"],
-    )
-
-    _write_csv_index(
-        work_dir / "review_index_deletions.csv",
-        deletions_index.values(),
-        ["sha256", "path", "reason", "group_id", "timestamp", "user"],
-    )
-
-    return {
-        "identical": identical_index,
-        "sequences": sequences_index,
-        "deletions": deletions_index,
-    }
-
-
-def _write_csv_index(path: Path, rows: list[dict[str, Any]] | Any, fieldnames: list[str]) -> None:
-    """Write index data to CSV file.
-
-    Args:
-        path: Output CSV file path
-        rows: Iterable of dictionaries to write
-        fieldnames: CSV column names
-    """
-    with path.open("w", newline="", encoding="utf-8") as f:
-        writer = csv.DictWriter(f, fieldnames=fieldnames)
-        writer.writeheader()
-        writer.writerows(rows)
+"""Functions for persisting and loading review decisions."""
+
+from __future__ import annotations
+
+import csv
+import json
+from pathlib import Path
+from typing import Any
+
+from utils.review_types import (
+    DeletionIndexEntry,
+    IdenticalDecision,
+    PhotoIdentifier,
+    ReviewIndexEntry,
+    SequenceDecision,
+)
+
+
+def append_decision_to_log(decision: IdenticalDecision | SequenceDecision, work_dir: Path) -> None:
+    """Append a review decision to the JSONL log.
+
+    Args:
+        decision: Decision object (IdenticalDecision or SequenceDecision)
+        work_dir: Work directory containing the log file
+    """
+    log_path: Path = work_dir / "review_decisions.jsonl"
+
+    # Ensure work directory exists
+    work_dir.mkdir(parents=True, exist_ok=True)
+
+    # Append decision as JSON line
+    with log_path.open("a", encoding="utf-8") as f:
+        json.dump(decision, f, ensure_ascii=False)
+        f.write("\n")
+
+
+def build_review_index(work_dir: Path) -> dict[str, Any]:
+    """Build in-memory indices from JSONL log and generate CSV files.
+
+    Reads review_decisions.jsonl and creates:
+    - review_index_identical.csv: identical group decisions
+    - review_index_sequences.csv: sequence group decisions
+    - review_index_deletions.csv: individual photo deletions
+
+    Args:
+        work_dir: Work directory containing the log file
+
+    Returns:
+        Dictionary with 'identical', 'sequences', and 'deletions' indices
+    """
+    log_path: Path = work_dir / "review_decisions.jsonl"
+
+    if not log_path.exists():
+        # No decisions yet, return empty indices
+        return {"identical": {}, "sequences": {}, "deletions": {}}
+
+    # Parse JSONL log
+    identical_index: dict[str, ReviewIndexEntry] = {}
+    sequences_index: dict[str, ReviewIndexEntry] = {}
+    deletions_index: dict[PhotoIdentifier, DeletionIndexEntry] = {}
+
+    with log_path.open(encoding="utf-8") as f:
+        for _line_num, raw_line in enumerate(f, 1):
+            line = raw_line.strip()
+            if not line:
+                continue
+
+            try:
+                decision: dict[str, Any] = json.loads(line)
+                decision_type: str | None = decision.get("type")
+
+                if decision_type == "identical":
+                    # Index identical group decision
+                    group_id: str = decision["group_id"]
+                    identical_index[group_id] = {
+                        "group_id": group_id,
+                        "decision_type": "identical",
+                        "action": decision["action"],
+                        "timestamp": decision["timestamp"],
+                        "user": decision["user"],
+                    }
+
+                    # Index deletions
+                    deleted_photos: list[tuple[str, str]] = decision.get("deleted_photos", [])
+                    sha256: str
+                    path: str
+                    for sha256, path in deleted_photos:
+                        deletions_index[(sha256, path)] = {
+                            "sha256": sha256,
+                            "path": path,
+                            "reason": "identical_group",
+                            "group_id": group_id,
+                            "timestamp": decision["timestamp"],
+                            "user": decision["user"],
+                        }
+
+                elif decision_type == "sequences":
+                    # Index sequence group decision
+                    seq_group_id: str = decision["group_id"]
+                    sequences_index[seq_group_id] = {
+                        "group_id": seq_group_id,
+                        "decision_type": "sequences",
+                        "action": decision["action"],
+                        "timestamp": decision["timestamp"],
+                        "user": decision["user"],
+                    }
+
+                    # Index deletions
+                    seq_deleted_photos: list[tuple[str, str]] = decision.get("deleted_photos", [])
+                    seq_sha256: str
+                    seq_path: str
+                    for seq_sha256, seq_path in seq_deleted_photos:
+                        deletions_index[(seq_sha256, seq_path)] = {
+                            "sha256": seq_sha256,
+                            "path": seq_path,
+                            "reason": "sequence_group",
+                            "group_id": seq_group_id,
+                            "timestamp": decision["timestamp"],
+                            "user": decision["user"],
+                        }
+
+            except json.JSONDecodeError:
+                continue
+
+    # Write CSV indices
+    _write_csv_index(
+        work_dir / "review_index_identical.csv",
+        identical_index.values(),
+        ["group_id", "decision_type", "action", "timestamp", "user"],
+    )
+
+    _write_csv_index(
+        work_dir / "review_index_sequences.csv",
+        sequences_index.values(),
+        ["group_id", "decision_type", "action", "timestamp", "user"],
+    )
+
+    _write_csv_index(
+        work_dir / "review_index_deletions.csv",
+        deletions_index.values(),
+        ["sha256", "path", "reason", "group_id", "timestamp", "user"],
+    )
+
+    return {
+        "identical": identical_index,
+        "sequences": sequences_index,
+        "deletions": deletions_index,
+    }
+
+
+def _write_csv_index(path: Path, rows: list[dict[str, Any]] | Any, fieldnames: list[str]) -> None:
+    """Write index data to CSV file.
+
+    Args:
+        path: Output CSV file path
+        rows: Iterable of dictionaries to write
+        fieldnames: CSV column names
+    """
+    with path.open("w", newline="", encoding="utf-8") as f:
+        writer = csv.DictWriter(f, fieldnames=fieldnames)
+        writer.writeheader()
+        writer.writerows(rows)

orchestrator/static/orchestrator.css

@@ -1,4 +1,4 @@
-/* Photo Dedup Orchestrator Styles */
+/* Photo Stack Finder Orchestrator Styles */
 
 :root {
     --primary-color: #2563eb;
@@ -520,78 +520,78 @@ h2 {
         max-height: 90vh;
     }
 }
-
-/* Info Section (Getting Started) */
-.info-section {
-    background: linear-gradient(135deg, #f0f9ff, #e0f2fe);
-    border-left: 4px solid var(--primary-color);
-    border-radius: 8px;
-    padding: 0;
-    margin-bottom: 2rem;
-    box-shadow: 0 2px 4px rgba(0, 0, 0, 0.05);
-}
-
-.info-section details summary {
-    padding: 1rem 1.5rem;
-    cursor: pointer;
-    user-select: none;
-    font-size: 1.1rem;
-    color: var(--primary-color);
-    list-style: none;
-}
-
-.info-section details summary::-webkit-details-marker {
-    display: none;
-}
-
-.info-section details[open] summary {
-    border-bottom: 1px solid var(--border-color);
-    margin-bottom: 1rem;
-}
-
-.info-section .info-content {
-    padding: 0 1.5rem 1.5rem 1.5rem;
-}
-
-.info-section h3 {
-    color: var(--text-primary);
-    margin-top: 1rem;
-    margin-bottom: 0.5rem;
-    font-size: 1.1rem;
-}
-
-.info-section ul, .info-section ol {
-    margin-left: 1.5rem;
-    margin-bottom: 1rem;
-}
-
-.info-section li {
-    margin-bottom: 0.5rem;
-}
-
-.info-section .checklist {
-    list-style: none;
-    margin-left: 0;
-}
-
-.info-section .checklist li {
-    padding-left: 1.5rem;
-    position: relative;
-}
-
-.info-section code {
-    background: rgba(0, 0, 0, 0.05);
-    padding: 0.2rem 0.4rem;
-    border-radius: 3px;
-    font-family: 'Consolas', 'Monaco', monospace;
-    font-size: 0.9em;
-}
-
-.info-section a {
-    color: var(--primary-color);
-    text-decoration: none;
-}
-
-.info-section a:hover {
-    text-decoration: underline;
-}
+
+/* Info Section (Getting Started) */
+.info-section {
+    background: linear-gradient(135deg, #f0f9ff, #e0f2fe);
+    border-left: 4px solid var(--primary-color);
+    border-radius: 8px;
+    padding: 0;
+    margin-bottom: 2rem;
+    box-shadow: 0 2px 4px rgba(0, 0, 0, 0.05);
+}
+
+.info-section details summary {
+    padding: 1rem 1.5rem;
+    cursor: pointer;
+    user-select: none;
+    font-size: 1.1rem;
+    color: var(--primary-color);
+    list-style: none;
+}
+
+.info-section details summary::-webkit-details-marker {
+    display: none;
+}
+
+.info-section details[open] summary {
+    border-bottom: 1px solid var(--border-color);
+    margin-bottom: 1rem;
+}
+
+.info-section .info-content {
+    padding: 0 1.5rem 1.5rem 1.5rem;
+}
+
+.info-section h3 {
+    color: var(--text-primary);
+    margin-top: 1rem;
+    margin-bottom: 0.5rem;
+    font-size: 1.1rem;
+}
+
+.info-section ul, .info-section ol {
+    margin-left: 1.5rem;
+    margin-bottom: 1rem;
+}
+
+.info-section li {
+    margin-bottom: 0.5rem;
+}
+
+.info-section .checklist {
+    list-style: none;
+    margin-left: 0;
+}
+
+.info-section .checklist li {
+    padding-left: 1.5rem;
+    position: relative;
+}
+
+.info-section code {
+    background: rgba(0, 0, 0, 0.05);
+    padding: 0.2rem 0.4rem;
+    border-radius: 3px;
+    font-family: 'Consolas', 'Monaco', monospace;
+    font-size: 0.9em;
+}
+
+.info-section a {
+    color: var(--primary-color);
+    text-decoration: none;
+}
+
+.info-section a:hover {
+    text-decoration: underline;
+}

orchestrator/static/orchestrator.html

@@ -3,14 +3,14 @@
 <head>
     <meta charset="UTF-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    <title>Photo Dedup Orchestrator</title>
+    <title>Photo Stack Finder Orchestrator</title>
     <link rel="icon" type="image/svg+xml" href="/static/favicon.svg">
     <link rel="stylesheet" href="/static/orchestrator.css">
 </head>
 <body>
     <div class="container">
         <header>
-            <h1>📸 Photo Deduplication Orchestrator</h1>
+            <h1>📸 Photo Stack Finder Orchestrator</h1>
             <p>Automated pipeline for finding and reviewing duplicate photos</p>
         </header>
 
@@ -22,7 +22,7 @@
                     <div class="info-content">
                         <h3>What This Tool Does</h3>
                         <p>
-                            Photo Dedup finds photos that originate from the <strong>same source image</strong>:
+                            Photo Stack Finder finds photos that originate from the <strong>same source image</strong>:
                             byte-identical files, different resolutions (low-res vs. high-res), edited versions vs. originals,
                             rotation variants, format conversions (JPEG vs. HEIC), and cloud sync duplicates like
                             <code>IMG_1234.jpg</code> and <code>IMG_1234(1).jpg</code>.
@@ -63,7 +63,7 @@
 
                         <p>
                             <strong>📖 Detailed Guide:</strong> See
-                            <a href="https://github.com/gbarrett28/photo_dedup/blob/master/GETTING_STARTED.md" target="_blank" rel="noopener">
+                            <a href="https://github.com/gbarrett28/photo_stack_finder/blob/master/GETTING_STARTED.md" target="_blank" rel="noopener">
                                 GETTING_STARTED.md
                             </a>
                             for step-by-step instructions including Google Takeout export.
@@ -84,7 +84,7 @@
                                    placeholder="/path/to/your/photos">
                             <button type="button" id="browse-source" class="btn-browse">📁 Browse</button>
                         </div>
-                        <small>Directory containing your photos to deduplicate</small>
+                        <small>Directory containing your photos to analyze</small>
                     </div>
 
                     <div class="form-group">
@@ -120,6 +120,12 @@
                                         Debug Mode (sequential processing)
                                     </label>
                                 </div>
+                                <div class="form-group">
+                                    <label for="skip-byte-identical">
+                                        <input type="checkbox" id="skip-byte-identical" name="skip_byte_identical" checked>
+                                        Skip byte-identical detection (trust SHA256 uniqueness)
+                                    </label>
+                                </div>
                             </div>
 
                             <div class="option-group">

orchestrator/static/orchestrator.js

@@ -1,4 +1,4 @@
-// Photo Dedup Orchestrator Client-side Logic
+// Photo Stack Finder Orchestrator Client-side Logic
 
 // State
 let currentBrowsePath = '';
@@ -313,6 +313,7 @@ function populateForm(config) {
     document.getElementById('max-workers').value = config.max_workers || '';
     document.getElementById('batch-size').value = config.batch_size || '';
     document.getElementById('debug-mode').checked = config.debug_mode || false;
+    document.getElementById('skip-byte-identical').checked = config.skip_byte_identical !== false; // Default true
 
     document.getElementById('comparison-method').value = config.comparison_method || 'SSIM';
     document.getElementById('ssim-threshold').value = config.gate_thresholds?.SSIM || 0.95;
@@ -369,6 +370,7 @@ async function handleFormSubmit(event) {
         max_workers: maxWorkers ? parseInt(maxWorkers) : null,
         batch_size: batchSize ? parseInt(batchSize) : null,
         debug_mode: formData.get('debug_mode') === 'on',
+        skip_byte_identical: formData.get('skip_byte_identical') === 'on',
         comparison_method: formData.get('comparison_method'),
         gate_thresholds: {
             SSIM: parseFloat(formData.get('ssim_threshold')),

overlap_metrics/__init__.py

@@ -40,7 +40,7 @@ if version.parse(scipy.__version__) < version.parse(MINIMUM_SCIPY_VERSION):
 
 # Version info
 __version__ = "1.0.0"
-__author__ = "Photo Deduplication Team"
+__author__ = "Photo Stack Finder Team"
 __description__ = "Distribution separation and overlap metrics with pluggable estimators"
 
 # Default metric suite for compute_suite()