Update

functions/build_lists.sh

@@ -51,7 +51,7 @@ format_file() {
     bash functions/tools.sh format "$1"
 }
 
-# Build list functions are to specify the syntax of the lists.
+# Build list functions are to specify the syntax of the lists for the build function.
 # $syntax: name of list syntax
 # $directory: directory to create list in
 # $comment: character used for comments (blank defaults to #)

functions/check_dead.sh

@@ -26,7 +26,7 @@ main() {
     check_alive
     update_light_file
 
-    # Cache dead domains (skip processing dead domains through alive check)
+    # Cache dead domains (done last to skip alive domains check)
     cat dead_in_raw.tmp >> "$DEAD_DOMAINS"
     format_file "$DEAD_DOMAINS"
 }
@@ -53,8 +53,8 @@ check_subdomains() {
 
     # Remove dead root domains from raw file and root domains file
     comm -23 "$RAW" <(printf "%s" "$dead_root_domains") > raw.tmp
-    mv raw.tmp "$RAW"
     comm -23 "$ROOT_DOMAINS" <(printf "%s" "$dead_root_domains") > root.tmp
+    mv raw.tmp "$RAW"
     mv root.tmp "$ROOT_DOMAINS"
 
     log_event "$dead_root_domains" dead raw
@@ -86,8 +86,8 @@ check_redundant() {
 
     # Remove unused wildcards from raw file and wildcards file
     comm -23 "$RAW" collated_dead_wildcards.tmp > raw.tmp
-    mv raw.tmp "$RAW"
     comm -23 "$WILDCARDS" collated_dead_wildcards.tmp > wildcards.tmp
+    mv raw.tmp "$RAW"
     mv wildcards.tmp "$WILDCARDS"
 
     log_event "$(<collated_dead_wildcards.tmp)" dead wildcard
@@ -127,7 +127,8 @@ check_alive() {
         alive_domains="$(printf "%s" "$alive_domains" | sed "s/^${subdomain}\.//" | sort -u)"
     done < "$SUBDOMAINS_TO_REMOVE"
 
-    printf "%s\n" "$alive_domains" >> "$RAW"  # Add resurrected domains to raw file
+    # Add resurrected domains to raw file
+    printf "%s\n" "$alive_domains" >> "$RAW"
     format_file "$RAW"
 
     log_event "$alive_domains" resurrected dead_domains_file

functions/check_parked.sh

@@ -23,11 +23,6 @@ main() {
 }
 
 remove_parked_domains() {
-    # Reset split files before run
-    find . -maxdepth 1 -type f -name "x??" -delete
-
-    printf "\n[start] Analyzing %s entries for parked domains\n" "$(wc -l < "$RAW")"
-
     # Retrieve parked domains and return if none found
     retrieve_parked "$RAW" || return
 
@@ -38,11 +33,6 @@ remove_parked_domains() {
 }
 
 add_unparked_domains() {
-    # Reset split files before run
-    find . -maxdepth 1 -type f -name "x??" -delete
-
-    printf "\n[start] Analyzing %s entries for unparked domains\n" "$(wc -l < "$PARKED_DOMAINS")"
-
     # Retrieve parked domains and return if none found
     retrieve_parked "$PARKED_DOMAINS" || return
 
@@ -66,7 +56,13 @@ add_unparked_domains() {
 # Output:
 #   exit status 1 if no parked domains were found
 retrieve_parked() {
-    : > parked_domains.tmp  # Truncate parked domains (prevents missing file error)
+    # Truncate parked domains (prevents missing file error)
+    : > parked_domains.tmp
+    # Truncate split files before run
+    find . -maxdepth 1 -type f -name "x??" -delete
+
+    printf "\n[info] Processing file %s\n
+        [start] Analyzing %s entries for parked domains\n" "$1" "$(wc -l < "$1")"
 
     # Split file into 12 equal files
     split -d -l $(($(wc -l < "$1")/12)) "$1"
@@ -160,4 +156,5 @@ cleanup() {
 }
 
 trap cleanup EXIT
+
 main

functions/tools.sh

@@ -2,6 +2,7 @@
 # Tools.sh is a shell wrapper intended to store commonly used functions.
 
 # Function 'format' is called to standardize the format of a file.
+# $1: file to be formatted
 format() {
     local -r file="$1"
     [[ ! -f "$file" ]] && return

functions/update_readme.sh

@@ -134,28 +134,28 @@ Thanks to the following people for the help, inspiration, and support!
 EOF
 }
 
-# Function 'print_stats' prints the various statistics for each source
-# $1: source to process (leave blank to process all sources).
+# Function 'print_stats' is an echo wrapper that returns the statistics for each source.
+# $1: source to process (default is all sources)
 print_stats() {
     [[ -n "$1" ]] && source="$1" || source='All sources'
     printf "%5s |%10s |%8s%% | %s\n" "$(sum "$TODAY" "$1")" \
         "$(sum "$YESTERDAY" "$1")" "$(sum_excluded "$1" )" "$source"
 }
 
-# Function 'sum' is an echo wrapper that sums up the domains retrieved by
-# that source for that particular day.
+# Function 'sum' is an echo wrapper that returns the total sum of domains retrieved
+# by that source for that particular day.
 # $1: day to process
-# $2: source to process
+# $2: source to process (default is all sources)
 sum() {
     # Print dash if no runs for that day found
     ! grep -qF "$1" "$SOURCE_LOG" && { printf "-"; return; }
     csvgrep -c 1 -m "$1" "$SOURCE_LOG" | csvgrep -c 2 -m "$2" | csvgrep -c 14 -m yes |
         csvcut -c 5 | awk '{total += $1} END {print total}'
 }
 
-# Function 'count_excluded' is an echo wrapper that counts the % of excluded domains
-# of raw count retrieved from each source.
-# $1: source to process
+# Function 'count_excluded' is an echo wrapper that returns the % of excluded domains
+# out of the raw count retrieved from each source.
+# $1: source to process (default is all sources)
 count_excluded() {
     csvgrep -c 2 -m "$1" "$SOURCE_LOG" | csvgrep -c 14 -m yes > source_rows.tmp
 
@@ -172,8 +172,8 @@ count_excluded() {
     printf "%s" "$((excluded_count*100/raw_count))"
 }
 
-# Function 'format_file' is a shell wrapper to standardize the format of a file
-# $1: file to format.
+# Function 'format_file' is a shell wrapper to standardize the format of a file.
+# $1: file to format
 format_file() {
     bash functions/tools.sh format "$1"
 }

functions/validate_raw.sh

@@ -114,7 +114,7 @@ validate_raw() {
 
         # Collate filtered wildcards to exclude from dead check
         printf "%s\n" "$wildcards" >> "$WILDCARDS"
-         # Collate filtered redundant domains for dead check
+        # Collate filtered redundant domains for dead check
         grep -Ff <(printf "%s" "$wildcards") redundant_domains.tmp >> "$REDUNDANT_DOMAINS"
 
         format_file "$WILDCARDS"
@@ -138,10 +138,9 @@ validate_raw() {
     printf "\n\e[1mProblematic domains (%s):\e[0m\n" "$(wc -l < filter_log.tmp)"
     sort -u filter_log.tmp
 
+    # Save changes to raw file and raw light file
     printf "%s\n" "$domains" > "$RAW"
     format_file "$RAW"
-
-    # Remove filtered domains from light file
     comm -12 "$RAW" "$RAW_LIGHT" > light.tmp && mv light.tmp "$RAW_LIGHT"
 
     total_whitelisted_count="$((whitelisted_count + whitelisted_tld_count))"