fleetd #639: redact block scalars by line number

scripts/config-edit.sh

@@ -154,18 +154,10 @@ done
 # story: a YAML block scalar (`|`, `|-`, `>`, `>-`, ...) puts the VALUE on the lines that follow
 # the key, each indented deeper than it. The key-name match above only ever sees the key line
 # itself, so those continuation lines used to flow straight through unredacted while the key line
-# right above them printed a reassuring "<redacted>" — an incomplete redactor that looks complete
-# is worse than one that visibly does nothing, because it stops a reviewer from looking further.
-# The fix is structural, not another name to match: once a key line is masked, every following
-# line indented STRICTLY DEEPER than that key is masked too, by indentation alone, until the
-# indentation returns to the key's own level or shallower. This needs no knowledge of the key's
-# name, so it covers a block scalar under any masked key — but ONLY while that key's own line is
-# itself inside the hunk being printed. `diff -u` prints just three lines of context, so a block
-# scalar's body often reaches this function with its key line left out; there is then nothing to
-# anchor to, `masked` is never set, and the body prints in full. A blank line inside a block
-# scalar loses the anchor the same way, because a blank diff line measures as indent 0. Both are
-# measured and filed as fleetd #639 — do not read this paragraph as a guarantee that a masked
-# key's value can never be printed.
+# right above them printed a reassuring "<redacted>". The redactor maps masked continuation lines
+# from each complete file before it reads the diff. It then masks a printed line when that file
+# line is inside a masked key's value. This covers block-scalar bodies even when the key line is
+# outside the printed hunk, and it keeps blank lines inside the value masked.
 #
 # `redact` is always fed `diff -u` output, and every line of a unified diff starts with exactly
 # one of ' ', '+', '-' (the three body markers; '@'/'-'/'+' for the three header-line kinds too).
@@ -174,37 +166,102 @@ done
 # column shallower than it really is, and either wrongly escapes a continuation mask or wrongly
 # ends one early. Tabs are out of scope: YAML forbids them for indentation, and this is a bounded
 # fix, not a YAML parser.
+map_masked_lines() {
+  local file="$1" side="$2" line content indent lead key line_number=0
+  local masked=0 masked_indent=0
+
+  case "$side" in
+    old) OLD_MASKED_LINES=() ;;
+    new) NEW_MASKED_LINES=() ;;
+    *) die "internal error: unknown redaction map side $side" ;;
+  esac
+
+  while IFS= read -r line || [ -n "$line" ]; do
+    line_number=$((line_number + 1))
+    content="$line"
+    indent=0
+    while [ "${content:$indent:1}" = " " ]; do indent=$((indent + 1)); done
+
+    if [ "$masked" = 1 ]; then
+      if [ -z "${content// /}" ] || [ "$indent" -gt "$masked_indent" ]; then
+        case "$side" in
+          old) OLD_MASKED_LINES[$line_number]=1 ;;
+          new) NEW_MASKED_LINES[$line_number]=1 ;;
+        esac
+        continue
+      fi
+      masked=0
+    fi
+
+    if [[ "$content" =~ ^([[:space:]]*)([A-Za-z0-9_.-]+:) ]]; then
+      lead="${BASH_REMATCH[1]}"
+      key="${BASH_REMATCH[2]}"
+      if [[ "$key" =~ (TOKEN|SECRET|PASSWORD|PASSWD|PASSPHRASE|CREDENTIAL|URI|_KEY) ]]; then
+        masked=1
+        masked_indent="$indent"
+      fi
+    fi
+  done < "$file"
+}
+
 redact() {
-  local line prefix content indent lead key
-  local masked=0 masked_indent=0 saved_nocasematch=0
+  local old_file="$1" new_file="$2"
+  local line prefix content indent lead key old_line=0 new_line=0 in_hunk=0
+  local old_masked new_masked saved_nocasematch=0
   shopt -q nocasematch && saved_nocasematch=1
   shopt -s nocasematch
-  sed -E 's#://[^@]*@#://<redacted>@#g' | while IFS= read -r line || [ -n "$line" ]; do
+
+  map_masked_lines "$old_file" old
+  map_masked_lines "$new_file" new
+
+  while IFS= read -r line || [ -n "$line" ]; do
+    if [[ "$line" =~ ^@@\ -([0-9]+)(,([0-9]+))?\ \+([0-9]+)(,([0-9]+))?\ @@ ]]; then
+      old_line="${BASH_REMATCH[1]}"
+      new_line="${BASH_REMATCH[4]}"
+      in_hunk=1
+      printf '%s\n' "$line"
+      continue
+    fi
+
     case "$line" in
       [\ +-]*) prefix="${line:0:1}"; content="${line:1}" ;;
       *)       prefix="";            content="$line" ;;
     esac
 
+    old_masked=0
+    new_masked=0
+    if [ "$in_hunk" = 1 ]; then
+      case "$prefix" in
+        ' ')
+          [ "${OLD_MASKED_LINES[$old_line]:-}" = 1 ] && old_masked=1
+          [ "${NEW_MASKED_LINES[$new_line]:-}" = 1 ] && new_masked=1
+          old_line=$((old_line + 1)); new_line=$((new_line + 1)) ;;
+        -)
+          [ "${OLD_MASKED_LINES[$old_line]:-}" = 1 ] && old_masked=1
+          old_line=$((old_line + 1)) ;;
+        +)
+          [ "${NEW_MASKED_LINES[$new_line]:-}" = 1 ] && new_masked=1
+          new_line=$((new_line + 1)) ;;
+      esac
+    fi
+
     indent=0
     while [ "${content:$indent:1}" = " " ]; do indent=$((indent + 1)); done
 
-    if [ "$masked" = 1 ] && [ "$indent" -gt "$masked_indent" ]; then
+    if [ "$old_masked" = 1 ] || [ "$new_masked" = 1 ]; then
       printf '%s%*s<redacted>\n' "$prefix" "$indent" ""
       continue
     fi
-    masked=0
 
     if [[ "$content" =~ ^([[:space:]]*)([A-Za-z0-9_.-]+:) ]]; then
       lead="${BASH_REMATCH[1]}"
       key="${BASH_REMATCH[2]}"
       if [[ "$key" =~ (TOKEN|SECRET|PASSWORD|PASSWD|PASSPHRASE|CREDENTIAL|URI|_KEY) ]]; then
         printf '%s%s%s <redacted>\n' "$prefix" "$lead" "$key"
-        masked=1
-        masked_indent="$indent"
         continue
       fi
     fi
-    printf '%s\n' "$line"
+    printf '%s\n' "$line" | sed -E 's#://[^@]*@#://<redacted>@#g'
   done
   [ "$saved_nocasematch" = 1 ] || shopt -u nocasematch
 }
@@ -627,7 +684,7 @@ run_edit() {
   apply_mode "$cand" "$orig_mode"
 
   say "change (redacted)"
-  diff -u "$backup" "$cand" | redact || true
+  diff -u "$backup" "$cand" | redact "$backup" "$cand" || true
 
   say "install"
   install_candidate "$cand" "$CONFIG" \
@@ -656,7 +713,7 @@ dry_run_diff() {
     die "candidate does not parse as valid YAML — this was a --dry-run, nothing would have been installed either"
   fi
   say "dry run — diff (redacted), nothing installed"
-  diff -u "$CONFIG" "$cand" | redact || true
+  diff -u "$CONFIG" "$cand" | redact "$CONFIG" "$cand" || true
   rm -f "$cand"; CAND=""
   return 0
 }