From 206d2d34f61d90da25d9710a5f46aa4b66933901 Mon Sep 17 00:00:00 2001
From: Jeff Smith <jeff@unbiasedgeek.com>
Date: Mon, 6 Apr 2026 14:26:37 -0600
Subject: [PATCH] feat: in-place per-file progress for classify, count, and
 large-file steps

---
 luminos.py               | 40 ++++++++++++++++++++++++++++++++++------
 luminos_lib/code.py      | 14 +++++++++++---
 luminos_lib/filetypes.py |  5 ++++-
 3 files changed, 49 insertions(+), 10 deletions(-)

diff --git a/luminos.py b/luminos.py
index 4e4bc45..0790041 100644
--- a/luminos.py
+++ b/luminos.py
@@ -3,8 +3,9 @@
 
 import argparse
 import json
-import sys
 import os
+import shutil
+import sys
 
 from luminos_lib.tree import build_tree, render_tree
 from luminos_lib.filetypes import classify_files, summarize_categories
@@ -15,6 +16,28 @@ from luminos_lib.watch import watch_loop
 from luminos_lib.report import format_report
 
 
+def _progress(label):
+    """Return (on_file, finish) for in-place per-file progress on stderr.
+
+    on_file(path) overwrites the current line with the label and truncated path.
+    finish() finalises the line with a newline.
+    """
+    cols = shutil.get_terminal_size((80, 20)).columns
+    prefix = f"  [scan] {label}... "
+    available = max(cols - len(prefix), 10)
+
+    def on_file(path):
+        rel = os.path.relpath(path)
+        if len(rel) > available:
+            rel = "..." + rel[-(available - 3):]
+        print(f"\r{prefix}{rel}\033[K", end="", file=sys.stderr, flush=True)
+
+    def finish():
+        print(f"\r{prefix}done\033[K", file=sys.stderr, flush=True)
+
+    return on_file, finish
+
+
 def scan(target, depth=3, show_hidden=False):
     """Run all analyses on the target directory and return a report dict."""
     report = {}
@@ -24,16 +47,21 @@ def scan(target, depth=3, show_hidden=False):
     report["tree"] = tree
     report["tree_rendered"] = render_tree(tree)
 
-    print("  [scan] Classifying files...", file=sys.stderr)
-    classified = classify_files(target, show_hidden=show_hidden)
+    on_file, finish = _progress("Classifying files")
+    classified = classify_files(target, show_hidden=show_hidden, on_file=on_file)
+    finish()
     report["file_categories"] = summarize_categories(classified)
     report["classified_files"] = classified
 
-    print("  [scan] Detecting languages and counting lines...", file=sys.stderr)
-    languages, loc = detect_languages(classified)
+    on_file, finish = _progress("Counting lines")
+    languages, loc = detect_languages(classified, on_file=on_file)
+    finish()
     report["languages"] = languages
     report["lines_of_code"] = loc
-    report["large_files"] = find_large_files(classified)
+
+    on_file, finish = _progress("Checking for large files")
+    report["large_files"] = find_large_files(classified, on_file=on_file)
+    finish()
 
     print("  [scan] Finding recently modified files...", file=sys.stderr)
     report["recent_files"] = find_recent_files(target, show_hidden=show_hidden)
diff --git a/luminos_lib/code.py b/luminos_lib/code.py
index 6d2571c..d6c5596 100644
--- a/luminos_lib/code.py
+++ b/luminos_lib/code.py
@@ -34,10 +34,11 @@ def _count_lines(filepath):
     return 0
 
 
-def detect_languages(classified_files):
+def detect_languages(classified_files, on_file=None):
     """Detect languages present and count lines of code per language.
 
     Returns (languages_set, loc_by_language).
+    on_file(path) is called per source file, if provided.
     """
     source_files = [f for f in classified_files if f["category"] == "source"]
     languages = set()
@@ -49,12 +50,17 @@ def detect_languages(classified_files):
         languages.add(lang)
         lines = _count_lines(f["path"])
         loc[lang] = loc.get(lang, 0) + lines
+        if on_file:
+            on_file(f["path"])
 
     return sorted(languages), loc
 
 
-def find_large_files(classified_files):
-    """Find files that are unusually large (>1000 lines or >10MB)."""
+def find_large_files(classified_files, on_file=None):
+    """Find files that are unusually large (>1000 lines or >10MB).
+
+    on_file(path) is called per source file checked, if provided.
+    """
     source_files = [f for f in classified_files if f["category"] == "source"]
     large = []
 
@@ -68,5 +74,7 @@ def find_large_files(classified_files):
         if reasons:
             large.append({"path": f["path"], "name": f["name"],
                           "reasons": reasons})
+        if on_file:
+            on_file(f["path"])
 
     return large
diff --git a/luminos_lib/filetypes.py b/luminos_lib/filetypes.py
index fa99abf..da47571 100644
--- a/luminos_lib/filetypes.py
+++ b/luminos_lib/filetypes.py
@@ -86,10 +86,11 @@ def _classify_one(filepath):
     return "unknown", desc
 
 
-def classify_files(target, show_hidden=False):
+def classify_files(target, show_hidden=False, on_file=None):
     """Walk the target directory and classify every file.
 
     Returns a list of dicts: {path, name, category, size, description}.
+    on_file(path) is called after each file is classified, if provided.
     """
     results = []
     for root, dirs, files in os.walk(target):
@@ -112,6 +113,8 @@ def classify_files(target, show_hidden=False):
                 "size": size,
                 "description": desc,
             })
+            if on_file:
+                on_file(full)
     return results