Normalize timestamp group folder names

grouping.py

@@ -12,11 +12,23 @@ Files are sorted by their current path and moved into one folder named
 from __future__ import annotations
 
 import os
+import re
 import shutil
 import sys
 from pathlib import Path
 
 
+ORDERED_TIMESTAMP_STEM_RE = re.compile(r"^(?P<timestamp>\d{8}_\d{6})-[1-9]\d*$")
+
+
+def group_stem(path: Path) -> str:
+    stem = path.stem
+    match = ORDERED_TIMESTAMP_STEM_RE.match(stem)
+    if match:
+        return match.group("timestamp")
+    return stem
+
+
 def unique_path(path: Path) -> Path:
     if not path.exists():
         return path
@@ -87,8 +99,8 @@ def group_items(items: list[Path]) -> Path | None:
         return None
 
     sorted_items = sorted(items, key=lambda item: item.name.lower())
-    first = sorted_items[0].stem
+    first = group_stem(sorted_items[0])
-    last = sorted_items[-1].stem
+    last = group_stem(sorted_items[-1])
     target_dir = unique_path(working_dir_for_items(sorted_items) / f"{first}-{last}")
     target_dir.mkdir(parents=True)
 

photo_metadata.py

@@ -84,6 +84,7 @@ TIME_ONLY_RE = re.compile(
 TZ_RE = re.compile(r"^(?P<sign>[+-])(?P<h>\d{1,2})(?::?(?P<m>\d{2}))?$")
 OFFSET_RE = re.compile(r"^([+-])(?:(\d+):)?(\d{1,2})(?::(\d{2}))?$")
 TOKEN_SHIFT_RE = re.compile(r"(\d+|[a-zA-Z]+)")
+ORDERED_TIMESTAMP_STEM_RE = re.compile(r"^(?P<timestamp>\d{8}_\d{6})-[1-9]\d*$")
 
 
 @dataclass
@@ -917,6 +918,14 @@ def normalized_extension(path: Path) -> str:
     return path.suffix.lower()
 
 
+def group_stem_from_name(name: str) -> str:
+    stem = Path(name).stem
+    match = ORDERED_TIMESTAMP_STEM_RE.match(stem)
+    if match:
+        return match.group("timestamp")
+    return stem
+
+
 def plan_names(records: list[MediaRecord], choices: UserChoices) -> None:
     if not choices.rename_files:
         for record in records:
@@ -981,12 +990,27 @@ def assign_groups(records: list[MediaRecord], groups: list[list[MediaRecord]]) -
             record.group_id = index
 
 
-def assign_group_names(groups: list[list[MediaRecord]]) -> None:
+def unique_group_name(base_name: str, working_dir: Path, used_names: set[str]) -> str:
+    if base_name not in used_names and not (working_dir / base_name).exists():
+        used_names.add(base_name)
+        return base_name
+
+    for index in range(1, 10000):
+        candidate = f"{base_name}-{index}"
+        if candidate not in used_names and not (working_dir / candidate).exists():
+            used_names.add(candidate)
+            return candidate
+
+    raise RuntimeError(f"Could not find an available group directory name for {base_name}")
+
+
+def assign_group_names(groups: list[list[MediaRecord]], working_dir: Path) -> None:
+    used_names: set[str] = set()
     for group in groups:
         ordered = sorted(group, key=photo_sort_key)
-        first = Path(ordered[0].final_name or ordered[0].path.name).stem
+        first = group_stem_from_name(ordered[0].final_name or ordered[0].path.name)
-        last = Path(ordered[-1].final_name or ordered[-1].path.name).stem
+        last = group_stem_from_name(ordered[-1].final_name or ordered[-1].path.name)
-        group_name = f"{first}-{last}"
+        group_name = unique_group_name(f"{first}-{last}", working_dir, used_names)
         for record in ordered:
             record.group_name = group_name
 
@@ -1165,7 +1189,7 @@ def prepare_plan(records: list[MediaRecord], choices: UserChoices) -> list[list[
 
     plan_names(records, choices)
     if groups:
-        assign_group_names(groups)
+        assign_group_names(groups, choices.working_dir)
     plan_targets(records, choices)
     return groups