vault-cli: extract to standalone repo, add flake.nix, move one-off scripts to scripts/one-off/

scripts/one-off/add_short_aliases.py

@@ -0,0 +1,108 @@
+#!/usr/bin/env python3
+"""Add a short-name alias (ID prefix stripped) to every ID-prefixed note's
+frontmatter, so Obsidian's alias-autocomplete can produce clean [[ID|Name]]
+links without the user typing the ID. Idempotent: skips notes that already
+have that alias or non-ID-prefixed notes.
+"""
+import os, re, sys
+
+VAULT = "/vault"
+# Matches "F.50.12 Jen", "R.31.10 Hindi", "F.22.11 Places We've Slept" etc.
+ID_TITLE_RE = re.compile(r'^([RJFI](?:\.\d+){1,3})\s+(.+)$')
+
+FRONTMATTER_RE = re.compile(r'^---\n(.*?)\n---\n', re.DOTALL)
+
+def split_frontmatter(text):
+    m = FRONTMATTER_RE.match(text)
+    if m:
+        return m.group(1), text[m.end():]
+    return None, text
+
+def add_alias(fm_text, alias):
+    lines = fm_text.split("\n") if fm_text else []
+    # find aliases: line (list style) or aliases: [a, b]
+    alias_line_idx = None
+    for i, l in enumerate(lines):
+        if re.match(r'^aliases\s*:', l):
+            alias_line_idx = i
+            break
+    if alias_line_idx is None:
+        lines.append(f"aliases:\n  - {alias}")
+        return "\n".join(lines)
+    line = lines[alias_line_idx]
+    # inline list form: aliases: [a, b]
+    m = re.match(r'^aliases\s*:\s*\[(.*)\]\s*$', line)
+    if m:
+        existing = [x.strip().strip('"\'') for x in m.group(1).split(",") if x.strip()]
+        if alias in existing:
+            return None  # already present
+        existing.append(alias)
+        lines[alias_line_idx] = "aliases: [" + ", ".join(existing) + "]"
+        return "\n".join(lines)
+    # block list form: aliases:\n  - a\n  - b
+    if line.strip() == "aliases:" or re.match(r'^aliases\s*:\s*$', line):
+        j = alias_line_idx + 1
+        existing = []
+        while j < len(lines) and re.match(r'^\s*-\s*', lines[j]):
+            existing.append(lines[j].strip()[2:].strip().strip('"\''))
+            j += 1
+        if alias in existing:
+            return None
+        lines.insert(j, f"  - {alias}")
+        return "\n".join(lines)
+    # single scalar alias: aliases: Foo
+    scalar = line.split(":", 1)[1].strip().strip('"\'')
+    if scalar == alias:
+        return None
+    lines[alias_line_idx] = "aliases:\n  - " + scalar + f"\n  - {alias}"
+    return "\n".join(lines)
+
+def main():
+    execute = "--execute" in sys.argv
+    changed = 0
+    skipped_no_id = 0
+    skipped_has_alias = 0
+    errors = []
+    for dp, _, fns in os.walk(VAULT):
+        if ".git" in dp.split(os.sep):
+            continue
+        for fn in fns:
+            if not fn.lower().endswith(".md"):
+                continue
+            base = fn[:-3]
+            m = ID_TITLE_RE.match(base)
+            if not m:
+                skipped_no_id += 1
+                continue
+            alias = m.group(2)
+            p = os.path.join(dp, fn)
+            try:
+                with open(p, "r", encoding="utf-8", errors="ignore") as f:
+                    text = f.read()
+            except Exception as e:
+                errors.append((p, str(e)))
+                continue
+            fm, rest = split_frontmatter(text)
+            new_fm = add_alias(fm or "", alias)
+            if new_fm is None:
+                skipped_has_alias += 1
+                continue
+            new_text = f"---\n{new_fm}\n---\n\n{rest.lstrip(chr(10))}" if fm is None else f"---\n{new_fm}\n---\n{rest}"
+            changed += 1
+            if execute:
+                with open(p, "w", encoding="utf-8") as f:
+                    f.write(new_text)
+
+    print(f"Notes with ID-prefixed title: {changed + skipped_has_alias}")
+    print(f"  Would add alias: {changed}")
+    print(f"  Already had alias: {skipped_has_alias}")
+    print(f"Notes without ID prefix (skipped, not applicable): {skipped_no_id}")
+    if errors:
+        print(f"Errors: {len(errors)}")
+        for p, e in errors[:10]:
+            print(f"  {p}: {e}")
+    if not execute:
+        print("\n(dry run -- pass --execute to write changes)")
+
+if __name__ == "__main__":
+    main()

scripts/one-off/find_unresolved_links.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python3
+"""Scan /vault for [[wikilinks]] and report which targets don't resolve
+to an actual note. Obsidian resolves links by basename match anywhere
+in the vault (unless the link includes a path), so we build an index
+of all note basenames (and their full relative paths) first.
+"""
+import os, re, json
+from collections import defaultdict
+
+VAULT = "/vault"
+LINK_RE = re.compile(r'\[\[([^\]|#]+)(?:#[^\]|]*)?(?:\|[^\]]*)?\]\]')
+
+def all_notes():
+    idx = defaultdict(list)  # basename (no ext, lowercase) -> [full paths]
+    all_paths = []
+    for dp, dirnames, fns in os.walk(VAULT):
+        if ".git" in dp.split(os.sep):
+            continue
+        for fn in fns:
+            if fn.lower().endswith(".md"):
+                p = os.path.join(dp, fn)
+                base = fn[:-3]
+                idx[base.lower()].append(p)
+                all_paths.append(p)
+    return idx, all_paths
+
+def resolve(link_target, index, current_dir):
+    # Obsidian: link may be a bare name, or a relative/vault path (with /)
+    target = link_target.strip()
+    if "/" in target:
+        # path-style link; try resolving relative to vault root or current dir
+        candidates = [
+            os.path.join(VAULT, target + ".md"),
+            os.path.join(VAULT, target),
+            os.path.join(current_dir, target + ".md"),
+            os.path.join(current_dir, target),
+        ]
+        for c in candidates:
+            if os.path.isfile(c):
+                return True
+        # also try basename match as fallback
+        base = os.path.basename(target)
+        return base.lower() in index
+    else:
+        return target.lower() in index
+
+def main():
+    index, all_paths = all_notes()
+    unresolved = defaultdict(list)  # target -> [source files]
+    total_links = 0
+    for p in all_paths:
+        try:
+            with open(p, "r", encoding="utf-8", errors="ignore") as f:
+                text = f.read()
+        except Exception:
+            continue
+        for m in LINK_RE.finditer(text):
+            target = m.group(1)
+            total_links += 1
+            if not resolve(target, index, os.path.dirname(p)):
+                unresolved[target].append(os.path.relpath(p, VAULT))
+
+    print(f"Total wikilinks scanned: {total_links}")
+    print(f"Unique unresolved targets: {len(unresolved)}")
+    print(f"Total unresolved link occurrences: {sum(len(v) for v in unresolved.values())}")
+
+    # dump full detail to json for further processing
+    out = {t: srcs for t, srcs in unresolved.items()}
+    with open("/tmp/unresolved_links.json", "w") as f:
+        json.dump(out, f, indent=2)
+    print("Full detail written to /tmp/unresolved_links.json")
+
+    # sorted by occurrence count desc
+    by_count = sorted(unresolved.items(), key=lambda kv: -len(kv[1]))
+    print("\n=== TOP 40 unresolved targets by occurrence count ===")
+    for target, srcs in by_count[:40]:
+        print(f"  {len(srcs):4d}x  [[{target}]]")
+
+if __name__ == "__main__":
+    main()

scripts/one-off/fix_wikilinks.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+"""Apply the two link-fix passes across /vault:
+1. fix_map: [[OldTarget]] -> [[NewNote|OldTarget]] (preserves display text)
+   Also handles piped/heading variants: [[OldTarget|Display]] -> [[NewNote|Display]]
+                                          [[OldTarget#Heading]] -> [[NewNote#Heading]]
+2. unlink_targets: [[Target]] -> Target (plain text, drop brackets)
+   Also handles piped: [[Target|Display]] -> Display
+"""
+import os, re, json, sys
+
+VAULT = "/vault"
+
+with open("/tmp/link_fix_map.json") as f:
+    FIX_MAP = json.load(f)
+with open("/tmp/unlink_targets.json") as f:
+    UNLINK = set(json.load(f))
+
+# Full link regex capturing target, optional #heading, optional |display
+LINK_RE = re.compile(r'\[\[([^\]|#]+)(#[^\]|]*)?(\|[^\]]*)?\]\]')
+
+def process_text(text):
+    changed = False
+    def repl(m):
+        nonlocal changed
+        target = m.group(1)
+        heading = m.group(2) or ""
+        pipe_display = m.group(3)  # includes leading |
+        target_stripped = target.strip()
+
+        if target_stripped in FIX_MAP:
+            new_target = FIX_MAP[target_stripped]
+            changed = True
+            if pipe_display:
+                # keep existing custom display text
+                return f"[[{new_target}{heading}{pipe_display}]]"
+            else:
+                # preserve original text as display so prose doesn't change visually
+                return f"[[{new_target}{heading}|{target_stripped}]]"
+
+        if target_stripped in UNLINK:
+            changed = True
+            if pipe_display:
+                display = pipe_display[1:]  # strip leading |
+                return display
+            else:
+                return target_stripped
+
+        return m.group(0)  # unchanged
+
+    new_text = LINK_RE.sub(repl, text)
+    return new_text, changed
+
+def main():
+    execute = "--execute" in sys.argv
+    files_changed = 0
+    total_fix_applied = 0
+    total_unlink_applied = 0
+
+    for dp, _, fns in os.walk(VAULT):
+        if ".git" in dp.split(os.sep):
+            continue
+        for fn in fns:
+            if not fn.lower().endswith(".md"):
+                continue
+            p = os.path.join(dp, fn)
+            try:
+                with open(p, "r", encoding="utf-8", errors="ignore") as f:
+                    text = f.read()
+            except Exception:
+                continue
+            new_text, changed = process_text(text)
+            if changed:
+                files_changed += 1
+                if execute:
+                    with open(p, "w", encoding="utf-8") as f:
+                        f.write(new_text)
+
+    print(f"Files changed: {files_changed}")
+    if not execute:
+        print("(dry run -- pass --execute to write)")
+
+if __name__ == "__main__":
+    main()

scripts/one-off/sort_unsorted.py

@@ -0,0 +1,163 @@
+#!/usr/bin/env python3
+"""Sort /data/_unsorted (old pre-RJFI JD tree) into /data/R,J,F,I storage tree.
+
+Dry-run by default; pass --execute to actually move files.
+"""
+import os, shutil, sys, csv
+
+UNSORTED = "/data/_unsorted"
+DATA = "/data"
+
+# old_prefix -> new_prefix (folder-level rename/move rules)
+# Order matters: longer/more specific prefixes first.
+MAPPING = [
+    # --- WhatsApp exports: wholesale move, old->new folder rename ---
+    ("1 Life admin/11 Me & other living things/11.54 Whatsapp exports",
+     "R Ryan/R.1 Life admin/R.11 Identity & vital records/R.11.54 Whatsapp exports"),
+
+    # --- 12 Home, house, and transport -> split F.11 (home) / F.12 (vehicles) ---
+    ("1 Life admin/12 Home, house, and transport/12.12 Home insurance & claims",
+     "F Family/F.1 Home, household & finances/F.11 Home & property/F.11.12 Home insurance & claims"),
+    ("1 Life admin/12 Home, house, and transport/12.21 Electricity, gas, & water",
+     "F Family/F.1 Home, household & finances/F.11 Home & property/F.11.21 Electricity, gas, & water"),
+    ("1 Life admin/12 Home, house, and transport/12.23 All other utilities & services",
+     "F Family/F.1 Home, household & finances/F.11 Home & property/F.11.23 All other utilities & services"),
+    ("1 Life admin/12 Home, house, and transport/12.24 Renovations & improvements",
+     "F Family/F.1 Home, household & finances/F.11 Home & property/F.11.24 Renovations & improvements"),
+    ("1 Life admin/12 Home, house, and transport/12.25 House repairs, maintenance, & upkeep",
+     "F Family/F.1 Home, household & finances/F.11 Home & property/F.11.24 Renovations & improvements"),
+    ("1 Life admin/12 Home, house, and transport/12.61 Move out of 6 Dorothy",
+     "F Family/F.1 Home, household & finances/F.11 Home & property/F.11.61 Move out of 6 Dorothy"),
+    ("1 Life admin/12 Home, house, and transport/12.30 Vehicles",
+     "F Family/F.1 Home, household & finances/F.12 Vehicles/F.12.30 Vehicles"),
+    ("1 Life admin/12 Home, house, and transport/12.32 Motor vehicle auto insurance & claims",
+     "F Family/F.1 Home, household & finances/F.12 Vehicles/F.12.32 Motor vehicle auto insurance & claims"),
+    ("1 Life admin/12 Home, house, and transport/12.33 Car repairs, maintenance, & upkeep",
+     "F Family/F.1 Home, household & finances/F.12 Vehicles/F.12.33 Car repairs, maintenance, & upkeep"),
+
+    # --- 13 Money -> split R.13 (solo) / F.13 (joint); tax + financial insurance are joint per design doc ---
+    ("1 Life admin/13 Money earned, spent, saved, & owed/13.54 Tax returns & accounting",
+     "F Family/F.1 Home, household & finances/F.13 Household finances/F.13.05 Tax returns & accounting"),
+    ("1 Life admin/13 Money earned, spent, saved, & owed/13.12 Financial insurance & claims",
+     "F Family/F.1 Home, household & finances/F.13 Household finances/F.13.12 Financial insurance & claims"),
+    ("1 Life admin/13 Money earned, spent, saved, & owed/13.44 Cryptocurrency",
+     "R Ryan/R.1 Life admin/R.13 Personal finance/R.13.44 Cryptocurrency"),
+
+    # --- 11 Me & other living things -> mostly R (Ryan personal) ---
+    ("1 Life admin/11 Me & other living things/11.11 Birth certificate & proof of name",
+     "R Ryan/R.1 Life admin/R.11 Identity & vital records/R.11.11 Birth certificate & proof of name"),
+    ("1 Life admin/11 Me & other living things/11.14 Licenses",
+     "R Ryan/R.1 Life admin/R.11 Identity & vital records/R.11.14 Licenses"),
+    ("1 Life admin/11 Me & other living things/11.16 Legal documents & certificates",
+     "R Ryan/R.1 Life admin/R.11 Identity & vital records/R.11.16 Legal documents & certificates"),
+    ("1 Life admin/11 Me & other living things/11.28 Reproductive health",
+     "R Ryan/R.1 Life admin/R.12 Health & body/R.12.28 Reproductive health"),
+    ("1 Life admin/11 Me & other living things/11.83 My library",
+     "R Ryan/R.1 Life admin/R.11 Identity & vital records/R.11.83 Ryan's library"),
+
+    # --- 15 Travel -> R.15 Travel (solo trips; matches exactly) ---
+    ("1 Life admin/15 Travel, events, & entertainment/15.41 All short trips",
+     "R Ryan/R.1 Life admin/R.15 Travel/R.15.41 All short trips"),
+
+    # --- 2 Career -> R.2 Career, ~1:1 ---
+    ("2 Career/21 Perfect Day", "R Ryan/R.2 Career/R.21 Perfect Day"),
+    ("2 Career/22 Sejour", "R Ryan/R.2 Career/R.22 Sejour"),
+    ("2 Career/23 Consulting", "R Ryan/R.2 Career/R.23 Consulting"),
+    ("2 Career/24 Stanford", "R Ryan/R.2 Career/R.24 Stanford"),
+    ("2 Career/29 Old applications & archives", "R Ryan/R.2 Career/R.29 Old applications & archives"),
+
+    # --- 3 Hobbies -> R.3 Hobbies, ~1:1 ---
+    ("3 Hobbies & interests/31 Language learning", "R Ryan/R.3 Hobbies & interests/R.31 Language learning"),
+    ("3 Hobbies & interests/36 Projects", "R Ryan/R.3 Hobbies & interests/R.36 Projects"),
+
+    # --- 4 Flying -> R.4 Flying, ~1:1 ---
+    ("4 Flying/41 Certification", "R Ryan/R.4 Flying/R.41 Certification, legal, & insurance"),
+    ("4 Flying/43 Resources", "R Ryan/R.4 Flying/R.43 Resources"),
+]
+
+# Items needing human judgment - do NOT auto-move, just report.
+FLAG_FOR_REVIEW = [
+    "1 Life admin/10 Management of area 10-19",  # SMS backups - unclear whose/where
+    "1 Life admin/11 Me & other living things/11.43 My family",  # Mom's book proposal
+    "1 Life admin/11 Me & other living things/11.09 Archive for category 11",  # AI deck for Jen
+    "1 Life admin/11 Me & other living things/11.71 My career sales pitch",
+    "1 Life admin/13 Money earned, spent, saved, & owed/13.41 Bank accounts",  # solo or joint?
+    "1 Life admin/13 Money earned, spent, saved, & owed/13.01 Inbox for category 13",
+    "1 Life admin/12 Home, house, and transport/12.01 Inbox for category 12",
+    "1 Life admin/14 My digital life/14.14 My data storage & backups",
+    "3 Hobbies & interests/30 Management for Hobbies",
+]
+
+
+def find_files(root):
+    for dirpath, _, filenames in os.walk(root):
+        for fn in filenames:
+            yield os.path.join(dirpath, fn)
+
+
+def plan_moves():
+    moves = []  # (src, dst)
+    unmatched = []
+    for src in find_files(UNSORTED):
+        rel = os.path.relpath(src, UNSORTED)
+        matched = False
+        for old_prefix, new_prefix in MAPPING:
+            if rel == old_prefix or rel.startswith(old_prefix + os.sep):
+                suffix = rel[len(old_prefix):]
+                dst = os.path.join(DATA, new_prefix.replace("/", os.sep) + suffix)
+                moves.append((src, dst))
+                matched = True
+                break
+        if not matched:
+            is_flagged = any(rel.startswith(f) for f in FLAG_FOR_REVIEW)
+            unmatched.append((rel, is_flagged))
+    return moves, unmatched
+
+
+def main():
+    execute = "--execute" in sys.argv
+    moves, unmatched = plan_moves()
+
+    print(f"=== PLANNED MOVES: {len(moves)} files ===")
+    by_target = {}
+    for src, dst in moves:
+        key = os.path.dirname(dst)
+        by_target[key] = by_target.get(key, 0) + 1
+    for k, v in sorted(by_target.items()):
+        print(f"  {v:5d} -> {k}")
+
+    print(f"\n=== FLAGGED FOR REVIEW (not moved): {sum(1 for _, f in unmatched if f)} files ===")
+    flagged_dirs = {}
+    for rel, is_flagged in unmatched:
+        if is_flagged:
+            d = os.path.dirname(rel)
+            flagged_dirs[d] = flagged_dirs.get(d, 0) + 1
+    for k, v in sorted(flagged_dirs.items()):
+        print(f"  {v:5d} :: {k}")
+
+    print(f"\n=== TRULY UNMATCHED (no mapping rule, not flagged): {sum(1 for _, f in unmatched if not f)} files ===")
+    other_dirs = {}
+    for rel, is_flagged in unmatched:
+        if not is_flagged:
+            d = os.path.dirname(rel)
+            other_dirs[d] = other_dirs.get(d, 0) + 1
+    for k, v in sorted(other_dirs.items()):
+        print(f"  {v:5d} :: {k}")
+
+    if execute:
+        print("\n=== EXECUTING MOVES ===")
+        moved = 0
+        for src, dst in moves:
+            os.makedirs(os.path.dirname(dst), exist_ok=True)
+            if os.path.exists(dst):
+                print(f"  SKIP (dst exists): {dst}")
+                continue
+            shutil.move(src, dst)
+            moved += 1
+        print(f"Moved {moved} files.")
+    else:
+        print("\n(dry run only -- pass --execute to actually move files)")
+
+
+if __name__ == "__main__":
+    main()

scripts/one-off/sort_unsorted_final.py

@@ -0,0 +1,45 @@
+#!/usr/bin/env python3
+"""Final placement pass for the 8 flagged/reviewed _unsorted items."""
+import os, shutil, sys
+
+U = "/data/_unsorted"
+D = "/data"
+
+MOVES = [
+    # (src relative to _unsorted, dst absolute under /data)
+    ("1 Life admin/10 Management of area 10-19/10.09 Archive for area 10-19/SMS Backups as of 2026-04-07/data",
+     "R Ryan/R.1 Life admin/R.11 Identity & vital records/R.11.55 SMS backups"),
+    ("1 Life admin/11 Me & other living things/11.09 Archive for category 11/2025-08-07 AI Deck for Jen.pdf",
+     "J Jen/J.0 Meta/J.00 Meta/J.00.01 Inbox for Jen/2025-08-07 AI Deck for Jen.pdf"),
+    ("1 Life admin/11 Me & other living things/11.43 My family/Moms Anandi Book & Screenplay/America's Niece - Proposal.pdf",
+     "F Family/F.5 People/F.50 Family/F.50.20 Pandyas/F.50.21 Nandini Pandya/America's Niece - Proposal.pdf"),
+    ("1 Life admin/11 Me & other living things/11.71 My career sales pitch/Ryan_Pandya_Resume___2024_10-1.pdf",
+     "R Ryan/R.2 Career/R.20 Curiosity/R.20.02 Resume/Ryan_Pandya_Resume___2024_10-1.pdf"),
+    ("1 Life admin/11 Me & other living things/11.71 My career sales pitch/Ryan_Pandya_Resume.pdf",
+     "R Ryan/R.2 Career/R.20 Curiosity/R.20.02 Resume/Ryan_Pandya_Resume.pdf"),
+    ("1 Life admin/12 Home, house, and transport/12.01 Inbox for category 12/2021-03-08 - 6 Dorothy sheet from Jason.pdf",
+     "F Family/F.1 Home, household & finances/F.11 Home & property/F.11.09 Old Homes/2021-2026 Dorothy/2021-03-08 - 6 Dorothy sheet from Jason.pdf"),
+    ("1 Life admin/13 Money earned, spent, saved, & owed/13.01 Inbox for category 13/Voided check.jpg",
+     "R Ryan/R.1 Life admin/R.13 Personal finance/R.13.01 Inbox/Voided check.jpg"),
+    ("1 Life admin/13 Money earned, spent, saved, & owed/13.41 Bank accounts/Ryan Wells Fargo direct deposit instructions.pdf",
+     "R Ryan/R.1 Life admin/R.13 Personal finance/R.13.01 Inbox/Ryan Wells Fargo direct deposit instructions.pdf"),
+    ("1 Life admin/14 My digital life/14.14 My data storage & backups/Google backup key.pdf",
+     "R Ryan/R.1 Life admin/R.14 My digital life/R.14.01 Inbox/Google backup key.pdf"),
+    ("3 Hobbies & interests/30 Management for Hobbies/30.01 Inbox for Hobbies/elixirbook.pdf",
+     "R Ryan/R.3 Hobbies & interests/R.35 Computers/R.35.21 Computer & programming language textbooks/elixirbook.pdf"),
+]
+
+execute = "--execute" in sys.argv
+for rel_src, rel_dst in MOVES:
+    src = os.path.join(U, rel_src)
+    dst = os.path.join(D, rel_dst)
+    exists = os.path.exists(src)
+    print(f"{'OK ' if exists else 'MISS'} {src} -> {dst}")
+    if execute and exists:
+        os.makedirs(os.path.dirname(dst), exist_ok=True)
+        shutil.move(src, dst)
+
+if execute:
+    print("Done.")
+else:
+    print("\n(dry run -- pass --execute)")