From 0726376955f38f60db7a51b862aafb6992dab866 Mon Sep 17 00:00:00 2001
From: epi052 <43392618+epi052@users.noreply.github.com>
Date: Sat, 26 Dec 2020 19:11:58 -0600
Subject: [PATCH] started documentation, fixed scanner option/result

---
 .github/workflows/build.yml | 2 +-
 README.md                   | 5 +++++
 ferox-config.toml.example   | 1 +
 src/scanner.rs              | 2 +-
 4 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 8d1bbee..c7480ea 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -5,7 +5,7 @@ on: [push]
 jobs:
   build-nix:
     runs-on: ${{ matrix.os }}
-    if: github.ref == 'refs/heads/master'
+#    if: github.ref == 'refs/heads/master'
     strategy:
       matrix:
         type: [ubuntu-x64, ubuntu-x86]
diff --git a/README.md b/README.md
index 2a35050..084c7b0 100644
--- a/README.md
+++ b/README.md
@@ -89,6 +89,8 @@ This attack is also known as Predictable Resource Location, File Enumeration, Di
     - [Filter Response Using a Regular Expression (new in `v1.8.0`)](#filter-response-using-a-regular-expression-new-in-v180)
     - [Stop and Resume Scans (save scan's state to disk) (new in `v1.9.0`)](#stop-and-resume-scans---resume-from-file-new-in-v190)
     - [Enforce a Time Limit on Your Scan (new in `v1.10.0`)](#enforce-a-time-limit-on-your-scan-new-in-v1100)
+    - [Extract Links from robots.txt (New in `v1.10.2`)](#extract-links-from-robotstxt-new-in-v1102)
+    - [Filter Response by Similarity to A Given Page (new in `v1.11.0`)](#filter-response-by-similarity-to-a-given-page-new-in-v1110)
 - [Comparison w/ Similar Tools](#-comparison-w-similar-tools)
 - [Common Problems/Issues (FAQ)](#-common-problemsissues-faq)
     - [No file descriptors available](#no-file-descriptors-available)
@@ -352,6 +354,7 @@ A pre-made configuration file with examples of all available settings can be fou
 # depth = 1
 # filter_size = [5174]
 # filter_regex = ["^ignore me$"]
+# filter_similar = ["https://somesite.com/soft404"]
 # filter_word_count = [993]
 # filter_line_count = [35, 36]
 # queries = [["name","value"], ["rick", "astley"]]
@@ -658,6 +661,8 @@ In addition to [extracting links from the response body](#extract-links-from-res
 `--extract-links` makes a request to `/robots.txt` and examines all `Allow` and `Disallow` entries.  Directory entries 
 are added to the scan queue, while file entries are requested and then reported if appropriate.  
 
+### Filter Response by Similarity to A Given Page (new in `v1.11.0`)
+
 ## 🧐 Comparison w/ Similar Tools
 
 There are quite a few similar tools for forced browsing/content discovery.  Burp Suite Pro, Dirb, Dirbuster, etc... 
diff --git a/ferox-config.toml.example b/ferox-config.toml.example
index 59a3d56..bfc801c 100644
--- a/ferox-config.toml.example
+++ b/ferox-config.toml.example
@@ -33,6 +33,7 @@
 # depth = 1
 # filter_size = [5174]
 # filter_regex = ["^ignore me$"]
+# filter_similar = ["https://somesite.com/soft404"]
 # filter_word_count = [993]
 # filter_line_count = [35, 36]
 # queries = [["name","value"], ["rick", "astley"]]
diff --git a/src/scanner.rs b/src/scanner.rs
index 0e745ce..da5d8bb 100644
--- a/src/scanner.rs
+++ b/src/scanner.rs
@@ -676,7 +676,7 @@ pub async fn initialize(num_words: usize, config: &Configuration) {
                 // if successful, create a filter based on the response's body
                 let fr = FeroxResponse::from(resp, true).await;
 
-                if let Ok(hash) = ssdeep::hash(fr.text().as_bytes()) {
+                if let Some(hash) = ssdeep::hash(fr.text().as_bytes()) {
                     // hash the response body and store the resulting has in the filter object
                     let filter = SimilarityFilter {
                         text: hash,